---
sidebar_position: 4
title: "Memory Providers"
description: "External memory provider plugins — Honcho, OpenViking, Mem0, Hindsight, Holographic, RetainDB, ByteRover, Supermemory"
---

# Memory Providers

Hermes Agent ships with 2 external memory provider plugins (RetainDB and ByteRover) that give the agent persistent, cross-session knowledge beyond the built-in MEMORY.md and USER.md, and more (such as Honcho, Hindsight, Supermemory and Holographic) are available from the [plugin catalog](./plugins.md). Only **one** external provider can be active at a time — the built-in memory is always active alongside it.

## Quick Start

```bash
hermes memory setup      # interactive picker + configuration
hermes memory status     # check what's active
hermes memory off        # disable external provider
```

You can also select the active memory provider via `hermes plugins` → Provider Plugins → Memory Provider.

Or set manually in `~/.hermes/config.yaml`:

```yaml
memory:
  provider: retaindb  # or byterover,
                      # or honcho / hindsight / supermemory / mem0 / openviking / holographic
                      # (plugin catalog — run `hermes plugins install <name>` first)
```

## How It Works

When a memory provider is active, Hermes automatically:

1. **Injects provider context** into the system prompt (what the provider knows)
2. **Prefetches relevant memories** before each turn (background, non-blocking)
3. **Syncs conversation turns** to the provider after each response
4. **Extracts memories on session end** (for providers that support it)
5. **Mirrors built-in memory writes** to the external provider
6. **Adds provider-specific tools** so the agent can search, store, and manage memories

The built-in memory (MEMORY.md / USER.md) continues to work exactly as before. The external provider is additive.

Everything Hermes hands a provider (turns, the transcript including tool output, recall queries, session-end and pre-compression transcripts, mirrored memory writes, delegation results and the arguments of the provider's own tools) passes through the same secret scrub as chat-platform and cron delivery first, so a key echoed into tool output is masked before the provider can store it. Like that delivery scrub it applies even with `security.redact_secrets: false`. Credentials with no recognisable shape (an arbitrary password, an opaque token outside a `key=value` or `Bearer` context) are not detected; your local transcript keeps the original text.

## Available Providers

### Honcho

:::info Plugin catalog
Honcho is maintained by [Plastic Labs](https://github.com/plastic-labs/honcho/tree/main/hermes-plugin-honcho) and installed from the [plugin catalog](./plugins.md) rather than bundled with Hermes. It is the same provider that used to ship in-tree: tools, config files and the `hermes honcho` commands are unchanged.
:::

AI-native cross-session user modeling with dialectic reasoning, session-scoped context injection, semantic search, and persistent conclusions. Base context now includes the session summary alongside user representation and peer cards, giving the agent awareness of what has already been discussed.

| | |
|---|---|
| **Best for** | Multi-agent systems with cross-session context, user-agent alignment |
| **Requires** | `hermes plugins install honcho` (installs the `honcho-ai` SDK with it); [API key](https://app.honcho.dev) or self-hosted instance |
| **Data storage** | Honcho Cloud or self-hosted |
| **Cost** | Honcho pricing (cloud) / free (self-hosted) |

**Tools (5):** `honcho_profile` (read/update peer card), `honcho_search` (semantic search), `honcho_context` (session context — summary, representation, card, messages), `honcho_reasoning` (LLM-synthesized), `honcho_conclude` (create/delete conclusions)

**Architecture:** Two-layer context injection — a base layer (session summary + representation + peer card, refreshed on `contextCadence`) plus a dialectic supplement (LLM reasoning, refreshed on `dialecticCadence`). The dialectic automatically selects cold-start prompts (general user facts) vs. warm prompts (session-scoped context) based on whether base context exists.

**Three orthogonal config knobs** control cost and depth independently:

- `contextCadence` — how often the base layer refreshes (API call frequency)
- `dialecticCadence` — how often the dialectic LLM fires (LLM call frequency)
- `dialecticDepth` — how many `.chat()` passes per dialectic invocation (1–3, depth of reasoning)

The auto-injected dialectic also scales its reasoning level by query length (longer query → deeper reasoning, capped at `reasoningLevelCap`); see [Query-Adaptive Reasoning Level](./honcho.md#query-adaptive-reasoning-level).

**Setup Wizard:**
```bash
hermes plugins install honcho   # from the plugin catalog
hermes memory setup             # select "honcho" — runs the Honcho-specific post-setup
```

The legacy `hermes honcho setup` command still works (it now redirects to `hermes memory setup`), but is only registered after Honcho is selected as the active memory provider.

**Headless / remote machines:** for cloud auth on a box without a browser (SSH, remote VM), pick **device** at the wizard's auth-method prompt. The CLI prints a short code and a verification link; open the link in a browser on any other machine, approve, and setup completes — no API key copy-paste. The wizard defaults to this option automatically when it detects no usable local browser.

**Config:** `$HERMES_HOME/honcho.json` (profile-local) or `~/.honcho/config.json` (global). Resolution order: `$HERMES_HOME/honcho.json` > `~/.hermes/honcho.json` > `~/.honcho/config.json`. See the [plugin README](https://github.com/plastic-labs/honcho/tree/main/hermes-plugin-honcho) and the [Honcho integration guide](https://docs.honcho.dev/v3/guides/integrations/hermes).

<details>
<summary>Full config reference</summary>

| Key | Default | Description |
|-----|---------|-------------|
| `apiKey` | -- | API key from [app.honcho.dev](https://app.honcho.dev) |
| `baseUrl` | -- | Base URL for self-hosted Honcho |
| `peerName` | -- | User peer identity |
| `aiPeer` | host key | AI peer identity (one per profile) |
| `workspace` | host key | Shared workspace ID |
| `contextTokens` | `null` (uncapped) | Token budget for auto-injected context per turn. Truncates at word boundaries |
| `contextCadence` | `1` | Minimum turns between `context()` API calls (base layer refresh) |
| `dialecticCadence` | `2` | Minimum turns between `peer.chat()` LLM calls. Recommended 1–5. Only applies to `hybrid`/`context` modes |
| `dialecticDepth` | `1` | Number of `.chat()` passes per dialectic invocation. Clamped 1–3. Pass 0: cold/warm prompt, pass 1: self-audit, pass 2: reconciliation |
| `dialecticDepthLevels` | `null` | Optional array of reasoning levels per pass, e.g. `["minimal", "low", "medium"]`. Overrides proportional defaults |
| `dialecticReasoningLevel` | `'low'` | Base reasoning level: `minimal`, `low`, `medium`, `high`, `max` |
| `dialecticDynamic` | `true` | When `true`, model can override reasoning level per-call via tool param |
| `dialecticMaxChars` | `600` | Max chars of dialectic result injected into system prompt |
| `recallMode` | `'hybrid'` | `hybrid` (auto-inject + tools), `context` (inject only), `tools` (tools only) |
| `writeFrequency` | `'async'` | When to flush messages: `async` (background thread), `turn` (sync), `session` (batch on end), or integer N |
| `saveMessages` | `true` | Whether to persist messages to Honcho API |
| `observationMode` | `'directional'` | `directional` (all on) or `unified` (shared pool). Override with `observation` object |
| `messageMaxChars` | `25000` | Max chars per message (chunked if exceeded) |
| `dialecticMaxInputChars` | `10000` | Max chars for dialectic query input to `peer.chat()` |
| `sessionStrategy` | `'per-directory'` | `per-directory`, `per-repo`, `per-session`, `global` |
| `pinUserPeer` | `false` | Gateway only. When `true`, every non-agent gateway user collapses to `peerName`; the pin overrides all aliases |
| `userPeerAliases` | `{}` | Gateway only. Maps runtime IDs to peers (`{"7654321": "alice"}`). Many-to-one |
| `runtimePeerPrefix` | `""` | Gateway only. Namespaces unknown runtime IDs (`telegram_7654321`) when no alias matches |

</details>

<details>
<summary>Minimal honcho.json (cloud)</summary>

```json
{
  "apiKey": "your-key-from-app.honcho.dev",
  "hosts": {
    "hermes": {
      "enabled": true,
      "aiPeer": "hermes",
      "peerName": "your-name",
      "workspace": "hermes"
    }
  }
}
```

</details>

<details>
<summary>Minimal honcho.json (self-hosted)</summary>

```json
{
  "baseUrl": "http://localhost:8000",
  "hosts": {
    "hermes": {
      "enabled": true,
      "aiPeer": "hermes",
      "peerName": "your-name",
      "workspace": "hermes"
    }
  }
}
```

</details>

:::tip Migrating from `hermes honcho`
If you previously used `hermes honcho setup`, your config and all server-side data are intact. Just re-enable through the setup wizard again or manually set `memory.provider: honcho` to reactivate via the new system.
:::

**Multi-peer setup:**

Honcho models conversations as peers exchanging messages — one user peer plus one AI peer per Hermes profile, all sharing a workspace. The workspace is the shared environment: the user peer is global across profiles, each AI peer is its own identity. Every AI peer builds an independent representation / card from its own observations, so a `coder` profile stays code-oriented while a `writer` profile stays editorial against the same user.

The mapping:

| Concept | What it is |
|---------|-----------|
| **Workspace** | Shared environment. All Hermes profiles under one workspace see the same user identity. |
| **User peer** (`peerName`) | The human. Shared across profiles in the workspace. |
| **AI peer** (`aiPeer`) | One per Hermes profile. Host key `hermes` → default; `hermes.<profile>` for others. |
| **Observation** | Per-peer toggles controlling what Honcho models from whose messages. `directional` (default, all four on) or `unified` (single-observer pool). |

### New profile, fresh Honcho peer

```bash
hermes profile create coder --clone
```

`--clone` creates a `hermes.coder` host block in `honcho.json` with `aiPeer: "coder"`, shared `workspace`, inherited `peerName`, `recallMode`, `writeFrequency`, `observation`, etc. The AI peer is eagerly created in Honcho so it exists before the first message.

### Existing profiles, backfill Honcho peers

```bash
hermes honcho sync
```

Scans every Hermes profile, creates host blocks for any profile without one, inherits settings from the default `hermes` block, and creates the new AI peers eagerly. Idempotent — skips profiles that already have a host block.

### Per-profile observation

Each host block can override the observation config independently. Example: a code-focused profile where the AI peer observes the user but doesn't self-model:

```json
"hermes.coder": {
  "aiPeer": "coder",
  "observation": {
    "user": { "observeMe": true, "observeOthers": true },
    "ai":   { "observeMe": false, "observeOthers": true }
  }
}
```

**Observation toggles (one set per peer):**

| Toggle | Effect |
|--------|--------|
| `observeMe` | Honcho builds a representation of this peer from its own messages |
| `observeOthers` | This peer observes the other peer's messages (feeds cross-peer reasoning) |

Presets via `observationMode`:

- **`"directional"`** (default) — all four flags on. Full mutual observation; enables cross-peer dialectic.
- **`"unified"`** — user `observeMe: true`, AI `observeOthers: true`, rest false. Single-observer pool; AI models the user but not itself, user peer only self-models.

Server-side toggles set via the [Honcho dashboard](https://app.honcho.dev) win over local defaults — synced back at session init.

See the [Honcho page](./honcho.md#observation-directional-vs-unified) for the full observation reference.

### Gateway identity mapping

The peer model above covers CLI, TUI, and desktop sessions, where every conversation resolves to `peerName`. The [gateway](../../developer-guide/gateway-internals.md) adds a second axis: users arrive with platform-native runtime IDs (Telegram UID, Discord snowflake, Slack user), and three keys decide which peer each ID resolves to.

| Key | Effect |
|-----|--------|
| `pinUserPeer: true` | Every non-agent gateway user collapses to `peerName`. The pin is checked first, so it overrides all aliases — pick it only when no user-side identity needs its own peer |
| `userPeerAliases` | Maps specific runtime IDs to peers (`{"7654321": "alice"}`). The home for routing distinct identities — including agents that each carry their own peer |
| `runtimePeerPrefix` | Namespaces any unmapped runtime ID (`telegram_7654321`) so platforms with same-shaped IDs don't collide |

Off-gateway these keys do nothing. `hermes memory setup` only prompts for them when it detects a connected gateway platform. See the [Honcho page](./honcho.md#gateway-identity-mapping) for the resolver ladder and the setup flow.

<details>
<summary>Full honcho.json example (multi-profile)</summary>

```json
{
  "apiKey": "your-key",
  "workspace": "hermes",
  "peerName": "eri",
  "hosts": {
    "hermes": {
      "enabled": true,
      "aiPeer": "hermes",
      "workspace": "hermes",
      "peerName": "eri",
      "recallMode": "hybrid",
      "writeFrequency": "async",
      "sessionStrategy": "per-directory",
      "observation": {
        "user": { "observeMe": true, "observeOthers": true },
        "ai": { "observeMe": true, "observeOthers": true }
      },
      "dialecticReasoningLevel": "low",
      "dialecticDynamic": true,
      "dialecticCadence": 2,
      "dialecticDepth": 1,
      "dialecticMaxChars": 600,
      "contextCadence": 1,
      "messageMaxChars": 25000,
      "saveMessages": true
    },
    "hermes.coder": {
      "enabled": true,
      "aiPeer": "coder",
      "workspace": "hermes",
      "peerName": "eri",
      "recallMode": "tools",
      "observation": {
        "user": { "observeMe": true, "observeOthers": false },
        "ai": { "observeMe": true, "observeOthers": true }
      }
    },
    "hermes.writer": {
      "enabled": true,
      "aiPeer": "writer",
      "workspace": "hermes",
      "peerName": "eri"
    }
  },
  "sessions": {
    "/home/user/myproject": "myproject-main"
  }
}
```

</details>

See the [plugin README](https://github.com/plastic-labs/honcho/tree/main/hermes-plugin-honcho) and [Honcho integration guide](https://docs.honcho.dev/v3/guides/integrations/hermes).

#### Upgrading from the bundled Honcho

Earlier Hermes releases shipped Honcho in-tree. If a profile still has `memory.provider: honcho`, Hermes installs the catalog plugin automatically the next time it starts or runs `hermes update` — your `~/.honcho/config.json` (or `$HERMES_HOME/honcho.json`), host blocks, peers and session mappings are read exactly as before, so no memory is lost. To do it by hand, or on a machine without network access at startup, run `hermes plugins install honcho`.


---

### OpenViking

:::info Plugin catalog
OpenViking is maintained by Volcengine and installed from the [plugin catalog](./plugins.md) rather than bundled with Hermes. Source: [volcengine/OpenViking — examples/hermes-plugin](https://github.com/volcengine/OpenViking/tree/main/examples/hermes-plugin). Existing setups are migrated automatically — see [Migrating from bundled OpenViking](#migrating-from-bundled-openviking).
:::

Context database by Volcengine (ByteDance) with filesystem-style knowledge hierarchy, tiered retrieval, and automatic memory extraction into 6 categories.

| | |
|---|---|
| **Best for** | Self-hosted knowledge management with structured browsing |
| **Requires** | `hermes plugins install openviking`; OpenViking initialized, validated, and running |
| **Data storage** | Self-hosted (local or cloud) |
| **Cost** | Free (open-source, AGPL-3.0) |

**Tools (6):** `viking_search` (semantic search), `viking_read` (tiered: abstract/overview/full), `viking_browse` (filesystem navigation), `viking_remember` (store facts), `viking_forget` (delete a memory file by exact `viking://` URI), `viking_add_resource` (ingest URLs/docs)

**Setup:**
```bash
# Prepare OpenViking first
openviking-server init
openviking-server doctor
openviking-server

# Then install and configure the Hermes plugin
hermes plugins install openviking
hermes memory setup    # select "openviking"
# Or manually:
hermes config set memory.provider openviking
```

`hermes memory setup` can reuse or copy connection values from
`~/.openviking/ovcli.conf`. Manual setup uses the active profile's `.env` file;
for the default profile that is `~/.hermes/.env`, and for named profiles use
`~/.hermes/profiles/<profile>/.env`.

```text
OPENVIKING_ENDPOINT=http://127.0.0.1:1933
# OPENVIKING_API_KEY=...
# OPENVIKING_ACCOUNT=default
# OPENVIKING_USER=default
```

OpenViking server settings live in `ov.conf` (`--config`,
`OPENVIKING_CONFIG_FILE`, or `~/.openviking/ov.conf`). Client connection values
live in `ovcli.conf` (`OPENVIKING_CLI_CONFIG_FILE` or
`~/.openviking/ovcli.conf`).

When the endpoint is local and nothing is listening, the plugin starts
`openviking-server` in the background. At the cataloged version that server
inherits the full Hermes process environment (minus `PYTHONPATH`), including
any bot, gateway or relay tokens set there. If that matters to you, start
`openviking-server` yourself before Hermes so the plugin never spawns it.
The fix is tracked upstream in
[volcengine/OpenViking#5553](https://github.com/volcengine/OpenViking/pull/5553).

**Key features:**
- Tiered context loading: L0 (~100 tokens) → L1 (~2k) → L2 (full)
- Automatic memory extraction on session commit (profile, preferences, entities, events, cases, patterns)
- `viking://` URI scheme for hierarchical knowledge browsing

`OPENVIKING_ACCOUNT` and `OPENVIKING_USER` are used for local/trusted mode.
Peer identity is optional. By default, Hermes sends no peer ID and writes
explicit memories to `viking://user/<user>/memories/...`. Setup does not ask
for a peer ID. For separate assistant context, set
`memory.openviking.agent: work-assistant` in `config.yaml`.

Existing non-empty peer settings keep their peer-scoped writes and recall.
This includes `OPENVIKING_AGENT` and `actor_peer_id` or legacy `agent_id` in a
linked OpenViking config. Existing memories are not moved or deleted.
With no peer ID, default search covers user memory and existing peer memories
under the same OpenViking user. Old peer memories remain searchable at their
existing paths. Ranking and result limits determine which memories are returned.
Set `memory.openviking.agent: hermes` to restore the old peer-scoped writes.
Memories written at user scope before this change stay there and remain
searchable. The setting changes future writes, not existing memory locations.

Hermes sends `User-Agent: openviking-memory-hermes/<version>` on OpenViking
requests. This standard harness identifier contains no per-user identifier and
does not add a separate request.

### Migrating from bundled OpenViking

OpenViking used to ship inside the Hermes tree. If your `config.yaml` already has `memory.provider: openviking`, there is nothing to do for most users:

- `hermes update` installs the catalog plugin into every profile home that names the provider.
- If the plugin is still missing on the first agent start (`hermes chat`, the gateway, Desktop), Hermes installs it and tells you it did.
- With `security.allow_lazy_installs: false` the agent-start path does not install anything; it prints the exact `hermes plugins install openviking` command instead.

`memory.provider`, `memory.openviking.*`, the `OPENVIKING_*` keys in `.env`, `~/.openviking/` and the memories on your OpenViking server are untouched. Verify with `hermes memory status` and `hermes plugins list`.

---

### Mem0

:::info Plugin catalog
Mem0 is maintained by Mem0 and installed from the [plugin catalog](./plugins.md) rather than bundled with Hermes. Source: [mem0ai/mem0 — integrations/hermes-plugin-mem0](https://github.com/mem0ai/mem0/tree/main/integrations/hermes-plugin-mem0). Existing setups are migrated automatically — see [Migrating from bundled Mem0](#migrating-from-bundled-mem0).
:::

Server-side LLM fact extraction with semantic search, reranking, and automatic deduplication. Three connection modes: **Platform** (Mem0 Cloud), **self-hosted dashboard** (a Mem0 server you run via Docker), and **OSS** (Mem0 in-process with your own LLM + vector store).

| | |
|---|---|
| **Best for** | Hands-off memory management — Mem0 handles extraction automatically |
| **Requires** | `hermes plugins install mem0` (installs the Mem0 SDK with the plugin); API key (platform), a running Mem0 server (self-hosted dashboard), or an LLM + vector store (OSS) |
| **Data storage** | Mem0 Cloud (platform), your own Mem0 server (self-hosted dashboard), or in-process (OSS) |
| **Cost** | Mem0 pricing (platform) / free (self-hosted or OSS) |

The mem0ai SDK sends anonymous PostHog usage telemetry unless `MEM0_TELEMETRY=false` is set in
your shell or `~/.hermes/.env`.

**Tools (4):** `mem0_search` (semantic search; optional reranking in platform mode, off by default), `mem0_add` (store verbatim facts), `mem0_update` (update by ID), `mem0_delete` (delete by ID)

**Setup (Platform):**
```bash
hermes plugins install mem0   # from the plugin catalog
hermes memory setup    # select "mem0" → "Platform"
# Or manually:
hermes config set memory.provider mem0
echo "MEM0_API_KEY=your-key" >> ~/.hermes/.env
```

**Setup (OSS):**
```bash
hermes memory setup    # select "mem0" → "Open Source (self-hosted)"
# Or via flags:
hermes memory setup mem0 --mode oss --oss-llm openai --oss-llm-key sk-... --oss-vector qdrant
```

Preview without writing files:
```bash
hermes memory setup mem0 --mode oss --oss-llm-key sk-... --dry-run
```

**Setup (Self-Hosted Dashboard):** connect to a Mem0 server you run via Docker (the dashboard's REST API):

```bash
hermes memory setup    # select "mem0" → "Self-hosted server"
# Or via flags:
hermes memory setup mem0 --mode selfhosted --host http://localhost:8888 --api-key your-admin-api-key
```

Or configure manually — either as env vars:

```bash
echo "MEM0_HOST=http://localhost:8888" >> ~/.hermes/.env
echo "MEM0_API_KEY=your-admin-api-key" >> ~/.hermes/.env
```

or in `mem0.json`:

```json
{ "host": "http://localhost:8888", "api_key": "your-admin-api-key" }
```

The plugin authenticates with `X-API-Key` and uses the server's `/search` / `/memories` routes. `api_key` is optional (omit only for `AUTH_DISABLED` servers). Don't set `mode: oss` — it takes precedence over `host`.

**Config:** `$HERMES_HOME/mem0.json` (behavioral settings). Only the secret `MEM0_API_KEY` belongs in `~/.hermes/.env`.

| Key | Default | Description |
|-----|---------|-------------|
| `mode` | `platform` | `platform` (Mem0 Cloud) or `oss` (self-managed, in-process) |
| `host` | — | Self-hosted Mem0 server URL (Docker dashboard). Routes over HTTP with `X-API-Key`; don't combine with `mode: oss` |
| `user_id` | `hermes-user` | User identifier |
| `agent_id` | `hermes` | Agent identifier |
| `rerank` | `false` | Rerank search results for relevance (platform mode only) |
| `sync_max_chars` | `450` | Per-message character cap applied before each turn is sent for fact extraction, cut at the last sentence boundary. The default fits 512-token embedders (Ollama `bge-small-zh-v1.5`, `all-minilm`); raise it (e.g. `6000`) for 8k-token embedders such as `text-embedding-3-small`, `jina-embeddings-v3` or `bge-m3` |

**OSS supported providers:**

| Component | Providers |
|-----------|-----------|
| LLM | openai, ollama |
| Embedder | openai, ollama |
| Vector Store | qdrant (local/server), pgvector |

**Switching modes:** Re-run `hermes memory setup mem0 --mode <platform|selfhosted|oss>` or edit `mem0.json` directly.

### Migrating from bundled Mem0

Mem0 used to ship inside the Hermes tree (and as the `hermes-agent[mem0]` pip extra). If your `config.yaml` already has `memory.provider: mem0`, there is nothing to do for most users:

- `hermes update` installs the catalog plugin into every profile home that names the provider.
- If the plugin is still missing on the first agent start (`hermes chat`, the gateway, Desktop), Hermes installs it and tells you it did.
- With `security.allow_lazy_installs: false` the agent-start path does not install anything; it prints the exact `hermes plugins install mem0` command instead.

`memory.provider`, `$HERMES_HOME/mem0.json`, the `MEM0_*` keys in `.env` and the memories stored in Mem0 Cloud, your Mem0 server or the local OSS store are untouched. Verify with `hermes memory status` and `hermes plugins list`.

---

### Hindsight

:::info Plugin catalog
Hindsight is maintained by [vectorize-io](https://github.com/vectorize-io/hindsight) and installed from the [plugin catalog](./plugins.md) rather than bundled with Hermes. Setup details live in the upstream docs: [hindsight.vectorize.io/sdks/integrations/hermes](https://hindsight.vectorize.io/sdks/integrations/hermes).
:::

Long-term memory with knowledge graph, entity resolution, and multi-strategy retrieval. The `hindsight_reflect` tool provides cross-memory synthesis that no other provider offers. Automatically retains full conversation turns (including tool calls) with session-level document tracking.

| | |
|---|---|
| **Best for** | Knowledge graph-based recall with entity relationships |
| **Requires** | `hermes plugins install hindsight`. Cloud: API key from [ui.hindsight.vectorize.io](https://ui.hindsight.vectorize.io). Local: LLM API key (OpenAI, Groq, OpenRouter, etc.) |
| **Data storage** | Hindsight Cloud, local embedded PostgreSQL, or an external local Hindsight server |
| **Cost** | Hindsight pricing (cloud) or free (local) |

**Tools:** `hindsight_retain` (store with entity extraction), `hindsight_recall` (multi-strategy search), `hindsight_reflect` (cross-memory synthesis)

**Setup:**
```bash
hermes plugins install hindsight   # from the plugin catalog; answer "Use 'hindsight' as the memory provider now?"
hermes memory setup                # select "hindsight"
# Or manually:
hermes config set memory.provider hindsight
echo "HINDSIGHT_API_KEY=your-key" >> ~/.hermes/.env
```

The plugin lands in `~/.hermes/plugins/hindsight/` (per profile home). A memory provider is activated by `memory.provider` in `config.yaml`, not `plugins.enabled`: accepting the install prompt (or passing `--enable`) sets it, and declining leaves it unchanged so `hermes memory setup` can pick it later. `hermes plugins enable hindsight` does not activate a memory provider. `hermes memory setup`, `hermes memory status`, `hermes plugins list` and the dashboard Memory settings all work with the catalog-installed plugin. In local embedded mode the plugin installs `hindsight-all` on first use through Hermes' lazy-install path, which honours `security.allow_lazy_installs`.

**Local mode UI:** `hindsight-embed -p hermes ui start`

**Config:** `$HERMES_HOME/hindsight/config.json`

| Key | Default | Description |
|-----|---------|-------------|
| `mode` | `cloud` | `cloud`, `local_embedded`, or `local_external` |
| `bank_id` | `hermes` | Memory bank identifier |
| `recall_budget` | `mid` | Recall thoroughness: `low` / `mid` / `high` |
| `memory_mode` | `hybrid` | `hybrid` (context + tools), `context` (auto-inject only), `tools` (tools only) |
| `auto_retain` | `true` | Automatically retain conversation turns |
| `auto_recall` | `true` | Automatically recall memories before each turn |
| `retain_async` | `true` | Process retain asynchronously on the server |
| `retain_context` | `conversation between Hermes Agent and the User` | Context label for retained memories |
| `retain_tags` | — | Default tags applied to retained memories; merged with per-call tool tags |
| `retain_source` | — | Optional `metadata.source` attached to retained memories |
| `retain_user_prefix` | `User` | Label used before user turns in auto-retained transcripts |
| `retain_assistant_prefix` | `Assistant` | Label used before assistant turns in auto-retained transcripts |
| `recall_tags` | — | Tags to filter on recall |

See the [upstream Hermes integration docs](https://hindsight.vectorize.io/sdks/integrations/hermes) for the full configuration reference.

#### Migrating from bundled Hindsight

Hindsight used to ship inside the Hermes tree (and as the `hermes-agent[hindsight]` pip extra). If your `config.yaml` already has `memory.provider: hindsight`, there is nothing to do for most users:

- `hermes update` installs the catalog plugin into every profile home that names the provider. Each line names the profile it is about. In a terminal it asks before preparing the plugin's Python dependencies; when several profiles use the provider, the questions are asked once and the answers apply to all of them. Without a terminal (the Desktop app, a script, a service) nobody can answer, so each profile prepares them unattended when its `security.allow_lazy_installs` is on (the default); a profile with it off gets the exact `hermes -p <profile> plugins install hindsight` command instead, and the other profiles still migrate.
- If the plugin is still missing on the first agent start (`hermes chat`, Desktop, the gateway, …), Hermes installs it, dependencies included, and shows ``✓ Memory provider 'hindsight' moved out of core — installed its plugin from the catalog (memory.provider and your stored memories are unchanged; check its settings with `hermes memory status`).`` Messaging platforms get the line with the first reply.
- When the agent-start install cannot happen, you see why instead of silently running without external memory: with `security.allow_lazy_installs: false` the warning names the install command for that profile; offline or declined installs show the error and the same command. After a failed attempt, agent starts in the next hour skip the install and only repeat the command; `hermes update` always retries.
- Agent start never asks a question (the chat prompt owns the terminal). A catalog provider that never shipped with Hermes (for example `mnemosyne`) is therefore not installed on agent start: the warning names `hermes plugins install <name>` for that profile, or install it from the dashboard/Desktop Plugins page.

What changes on disk: the plugin appears in `~/.hermes/plugins/hindsight/` and `config.yaml` gains `plugins.enabled: [hindsight]`. `memory.provider`, `$HERMES_HOME/hindsight/config.json`, `HINDSIGHT_API_KEY` in `.env` and your memory bank data are untouched. Verify with `hermes memory status` (provider active) and `hermes plugins list` (plugin installed and enabled).

:::warning Where the plugin reads its config
Hindsight reads `$HERMES_HOME/hindsight/config.json` (per profile home), `~/.hindsight/config.json` (legacy shared), and the `HINDSIGHT_*` variables in `.env`. It does not read a `memory.hindsight` section of `config.yaml`: a `memory.hindsight.*` key there is ignored. Edit the plugin's own `config.json` (key table above) or use `hermes memory setup`.
:::

---

### Holographic

:::info Plugin catalog
Holographic is maintained by [itpartypattaya](https://github.com/itpartypattaya/hermes-plugin-holographic) and installed from the [plugin catalog](./plugins.md) rather than bundled with Hermes. It is the provider that used to ship in-tree, with the same provider name, settings and database. Existing setups are migrated automatically — see [Migrating from bundled Holographic](#migrating-from-bundled-holographic).
:::

Local SQLite fact store with FTS5 full-text search, trust scoring, and HRR (Holographic Reduced Representations) for compositional algebraic queries.

| | |
|---|---|
| **Best for** | Local-only memory with advanced retrieval, no external dependencies |
| **Requires** | Nothing (SQLite is always available). NumPy optional for HRR algebra. |
| **Data storage** | Local SQLite |
| **Cost** | Free |

**Tools:** `fact_store` (9 actions: add, search, probe, related, reason, contradict, update, remove, list), `fact_feedback` (helpful/unhelpful rating that trains trust scores)

**Setup:**
```bash
hermes plugins install holographic   # from the plugin catalog
hermes memory setup                  # select "holographic"
# Or manually:
hermes config set memory.provider holographic
```

**Config:** `config.yaml` under `plugins.hermes-memory-store`

| Key | Default | Description |
|-----|---------|-------------|
| `db_path` | `$HERMES_HOME/memory_store.db` | SQLite database path |
| `auto_extract` | `false` | Auto-extract facts at session end |
| `default_trust` | `0.5` | Default trust score (0.0–1.0) |

**Unique capabilities:**
- `probe` — entity-specific algebraic recall (all facts about a person/thing)
- `reason` — compositional AND queries across multiple entities
- `contradict` — automated detection of conflicting facts
- Trust scoring with asymmetric feedback (+0.05 helpful / -0.10 unhelpful)

The catalog plugin has its own release notes and options beyond this list; see its [README](https://github.com/itpartypattaya/hermes-plugin-holographic) for the current tool actions and settings.

#### Migrating from bundled Holographic

Holographic used to ship inside the Hermes tree. If your `config.yaml` already has `memory.provider: holographic`, there is nothing to do:

- `hermes update` installs the catalog plugin into every profile home that names the provider.
- If the plugin is still missing on the first agent start (`hermes chat`, the gateway, Desktop), Hermes installs it and tells you it did.
- With `security.allow_lazy_installs: false` the agent-start path does not install anything; it prints the exact `hermes plugins install holographic` command instead.

Your facts (`$HERMES_HOME/memory_store.db`, or the `db_path` you set) and your `plugins.hermes-memory-store` settings are read exactly as before, so no memory is lost. Verify with `hermes memory status` and `hermes plugins list`.

If you installed Nous Research's interim copy by URL (`NousResearch/hermes-plugin-holographic`, now archived), `hermes plugins update holographic` moves it onto the catalog entry; your data stays where it is.

---

### RetainDB

Cloud memory API with hybrid search (Vector + BM25 + Reranking), 7 memory types, and delta compression.

| | |
|---|---|
| **Best for** | Teams already using RetainDB's infrastructure |
| **Requires** | RetainDB account + API key |
| **Data storage** | RetainDB Cloud |
| **Cost** | $20/month |

**Tools (10):** `retaindb_profile` (user profile), `retaindb_search` (semantic search), `retaindb_context` (task-relevant context), `retaindb_remember` (store with type + importance), `retaindb_forget` (delete memories), plus file tools: `retaindb_upload_file`, `retaindb_list_files`, `retaindb_read_file`, `retaindb_ingest_file`, `retaindb_delete_file`

**Setup:**
```bash
hermes memory setup    # select "retaindb"
# Or manually:
hermes config set memory.provider retaindb
echo "RETAINDB_API_KEY=your-key" >> ~/.hermes/.env
```

---

### ByteRover

Persistent memory via the `brv` CLI — hierarchical knowledge tree with tiered retrieval (fuzzy text → LLM-driven search). Local-first with optional cloud sync.

| | |
|---|---|
| **Best for** | Developers who want portable, local-first memory with a CLI |
| **Requires** | ByteRover CLI (`npm install -g byterover-cli` or [install script](https://byterover.dev)) |
| **Data storage** | Local (default) or ByteRover Cloud (optional sync) |
| **Cost** | Free (local) or ByteRover pricing (cloud) |

**Tools:** `brv_query` (search knowledge tree), `brv_curate` (store facts/decisions/patterns), `brv_status` (CLI version + tree stats)

**Setup:**
```bash
# Install the CLI first
curl -fsSL https://byterover.dev/install.sh | sh

# Then configure Hermes
hermes memory setup    # select "byterover"
# Or manually:
hermes config set memory.provider byterover
```

**Key features:**
- Automatic pre-compression extraction (saves insights before context compression discards them)
- Knowledge tree stored at `$HERMES_HOME/byterover/` (profile-scoped)
- SOC2 Type II certified cloud sync (optional)

---

### Supermemory

:::info Plugin catalog
Supermemory is maintained by Supermemory and installed from the [plugin catalog](./plugins.md) rather than bundled with Hermes. Source and full configuration reference: [supermemoryai/hermes-supermemory](https://github.com/supermemoryai/hermes-supermemory). Existing setups are migrated automatically — see [Migrating from bundled Supermemory](#migrating-from-bundled-supermemory).
:::

Semantic long-term memory with profile recall, semantic search, explicit memory tools, and per-turn conversation capture (one document per session per 4-hour window).

| | |
|---|---|
| **Best for** | Semantic recall with user profiling and session-level graph building |
| **Requires** | `hermes plugins install supermemory` (installs the Supermemory SDK with the plugin); [cloud API key](http://app.supermemory.ai/integrations?connect=hermes), or a [self-hosted server](https://supermemory.ai/docs/self-hosting/overview) |
| **Data storage** | Supermemory Cloud or self-hosted |
| **Cost** | Supermemory pricing (cloud) / free (self-hosted) |

**Tools:** `supermemory_store` (save explicit memories), `supermemory_search` (semantic similarity search), `supermemory_forget` (forget by ID or best-match query), `supermemory_profile` (persistent profile + recent context)

**Setup:**
```bash
hermes plugins install supermemory   # from the plugin catalog
hermes memory setup                  # select "supermemory"
# Or manually:
hermes config set memory.provider supermemory
echo 'SUPERMEMORY_API_KEY=***' >> ~/.hermes/.env
```

Self-hosted setup:

```bash
npx supermemory local
```

After `hermes plugins install supermemory` and before running `hermes memory setup`, set `base_url` in
`$HERMES_HOME/supermemory.json`:

```json
{
  "base_url": "http://localhost:6767"
}
```

Then run `hermes memory setup` and enter the API key printed by the local
server. Configuring the endpoint first ensures the setup connection probe also
stays local.

**Config:** `$HERMES_HOME/supermemory.json`

| Key | Default | Description |
|-----|---------|-------------|
| `base_url` | `https://api.supermemory.ai` | API endpoint for hosted or self-hosted Supermemory. Takes priority over `SUPERMEMORY_BASE_URL`. |
| `container_tag` | `hermes` | Container tag used for search and writes. Supports `{identity}` template for profile-scoped tags. |
| `auto_recall` | `true` | Inject relevant memory context before turns |
| `auto_capture` | `true` | Store cleaned user-assistant turns after each response |
| `max_recall_results` | `10` | Max recalled items to format into context |
| `profile_frequency` | `50` | Include profile facts on first turn and every N turns |
| `capture_mode` | `all` | Skip tiny or trivial turns by default |
| `search_mode` | `hybrid` | Search mode: `hybrid`, `memories`, or `documents` |
| `api_timeout` | `5.0` | Timeout for SDK requests |

**Environment variables:** `SUPERMEMORY_API_KEY` (required), `SUPERMEMORY_BASE_URL` (compatibility fallback when `base_url` is not configured), `SUPERMEMORY_CONTAINER_TAG` (overrides config).

Base URL precedence is `supermemory.json` → `SUPERMEMORY_BASE_URL` → `https://api.supermemory.ai`. SDK operations and setup/status probes all use the resolved endpoint.

**Key features:**
- Automatic context fencing — strips recalled memories from captured turns to prevent recursive memory pollution
- Per-turn capture — each completed turn is written as it happens, one document per session per 4-hour window
- Failed turn writes are retried (at-least-once) on the next turn, session end, `/reset`, or shutdown
- End-to-end self-hosted routing — SDK and probe requests use the same configured endpoint
- Profile facts injected on first turn and at configurable intervals
- **Profile-scoped containers** — use `{identity}` in `container_tag` (e.g. `hermes-{identity}` → `hermes-coder`) to isolate memories per Hermes profile
- **Multi-container mode** — enable `enable_custom_container_tags` with a `custom_containers` list to let the agent read/write across named containers. Automatic operations stay on the primary container.

<details>
<summary>Multi-container example</summary>

```json
{
  "container_tag": "hermes",
  "enable_custom_container_tags": true,
  "custom_containers": ["project-alpha", "shared-knowledge"],
  "custom_container_instructions": "Use project-alpha for coding context."
}
```

</details>

**Support:** [Discord](https://supermemory.link/discord) · [support@supermemory.com](mailto:support@supermemory.com)

### Migrating from bundled Supermemory

Supermemory used to ship inside the Hermes tree (and as the `hermes-agent[supermemory]` pip extra). If your `config.yaml` already has `memory.provider: supermemory`, there is nothing to do for most users:

- `hermes update` installs the catalog plugin into every profile home that names the provider (this runs even when `security.allow_lazy_installs` is `false`).
- If the plugin is still missing on the first agent start (`hermes chat`, the gateway, …), Hermes installs it and prints `✓ Memory provider 'supermemory' moved out of core — installed its plugin from the catalog (your memory.supermemory settings and data are unchanged).`
- With `security.allow_lazy_installs: false`, the agent-start path instead logs one line — ``Memory provider 'supermemory' is not installed; security.allow_lazy_installs is off — run `hermes plugins install supermemory`.`` — and you run `hermes plugins install supermemory` yourself.

What changes on disk: the plugin appears in `~/.hermes/plugins/supermemory/` and `config.yaml` gains `plugins.enabled: [supermemory]`. The Supermemory SDK is installed from the plugin's own package metadata, so the `hermes-agent[supermemory]` extra is no longer needed. `memory.provider`, `$HERMES_HOME/supermemory.json`, the `SUPERMEMORY_*` keys in `.env` and the memories stored in your Supermemory account are untouched. Verify with `hermes memory status` (provider active) and `hermes plugins list` (plugin installed and enabled).

### Memori

Structured long-term memory using Memori Cloud, with background completed-turn capture, tool-aware turn context, and explicit recall tools for facts, summaries, quota, signup, and feedback.

| | |
|---|---|
| **Best for** | Agent-controlled recall with structured project and session attribution |
| **Requires** | Externally supplied `hermes-memori` CLI and provider integration + [Memori API key](https://app.memorilabs.ai/signup) |
| **Data storage** | Memori Cloud |
| **Cost** | Memori pricing |

**Tools:** `memori_recall` (search long-term memory), `memori_recall_summary` (summarized context), `memori_quota` (usage/quota), `memori_signup` (request signup email), `memori_feedback` (send integration feedback)

**Setup:**

`hermes-memori` is an external integration, not a managed PM tool name. Follow
its publisher's instructions to install the CLI in an independent environment.
Before running its installer, confirm that it targets the intended Hermes home
and supplies a provider with declared Python dependencies. Do not let an external
installer pip-install into Hermes's selected environment. CLI availability alone
does not make the Python provider available inside Hermes; an entry-point-only
distribution needs an owner-managed build that includes it.

```bash
# Run only after confirming the external installer's integration contract above.
hermes-memori install
hermes config set memory.provider memori
hermes memory setup
```

If the installer does not support PM-managed directory-provider admission, ask
the publisher for that integration rather than inventing a `hermes pm install`
package command. Restart Hermes after successful dependency preparation.

---

## Provider Comparison

| Provider | Storage | Cost | Tools | Dependencies | Unique Feature |
|----------|---------|------|-------|-------------|----------------|
| **Honcho** (plugin catalog) | Cloud/Self-hosted | Paid/Free | 5 | `hermes plugins install honcho` | Dialectic user modeling + session-scoped context |
| **OpenViking** (plugin catalog) | Self-hosted | Free | 6 | `hermes plugins install openviking` + server | Filesystem hierarchy + tiered loading |
| **Mem0** (plugin catalog) | Cloud/Self-hosted | Free/Paid | 4 | `hermes plugins install mem0` | Server-side LLM extraction + self-hosted/OSS modes |
| **Hindsight** (plugin catalog) | Cloud/Local | Free/Paid | 3 | `hermes plugins install hindsight` | Knowledge graph + reflect synthesis |
| **Holographic** (plugin catalog) | Local | Free | 2 | `hermes plugins install holographic` | HRR algebra + trust scoring |
| **RetainDB** | Cloud | $20/mo | 10 | `requests` | Delta compression |
| **ByteRover** | Local/Cloud | Free/Paid | 3 | `brv` CLI | Pre-compression extraction |
| **Supermemory** (plugin catalog) | Cloud/Self-hosted | Free/Paid | 4 | `hermes plugins install supermemory` | Context fencing + session graph ingest + multi-container |
| **Memori** | Cloud | Free/Paid | 5 | `hermes-memori` | Tool-aware memory + structured recall |

## Profile Isolation

Each provider's data is isolated per [profile](../profiles.md):

- **Local storage providers** (Holographic, ByteRover) use `$HERMES_HOME/` paths which differ per profile
- **Config file providers** (Honcho, Mem0, Hindsight, Supermemory) store config in `$HERMES_HOME/` so each profile has its own credentials
- **Cloud providers** (RetainDB) auto-derive profile-scoped project names
- **Env var providers** (OpenViking) are configured via each profile's `.env` file

## Providers Moving to the Plugin Catalog

Memory providers are moving out of the Hermes tree into their maintainers' own repositories,
published through the [plugin catalog](./plugins.md). Hindsight moved first (see
[Migrating from bundled Hindsight](#migrating-from-bundled-hindsight)), then Honcho (see
[Upgrading from the bundled Honcho](#upgrading-from-the-bundled-honcho)), Supermemory (see
[Migrating from bundled Supermemory](#migrating-from-bundled-supermemory)), Mem0 (see
[Migrating from bundled Mem0](#migrating-from-bundled-mem0)) and OpenViking (see
[Migrating from bundled OpenViking](#migrating-from-bundled-openviking)) and Holographic (now
maintained by itpartypattaya, see
[Migrating from bundled Holographic](#migrating-from-bundled-holographic)). RetainDB and
ByteRover leave core on October 15, 2026; their standalone repositories are unmaintained and
open for a new maintainer. Nothing changes for you: the
provider name, the settings it reads, its data directory and its tools stay the same.
When a provider you have configured stops shipping with Hermes, `hermes update` installs its
catalog plugin for every profile that names it; if you update through the Desktop app, the
agent does the same the first time it starts. Every outcome is shown to you — in the terminal,
in Desktop, or with the first reply on a messaging platform. If the install cannot happen
(`security.allow_lazy_installs: false`, offline, declined), the warning includes the exact
`hermes plugins install <name>` command.

## Building a Memory Provider

See the [Developer Guide: Memory Provider Plugins](../../developer-guide/memory-provider-plugin.md) for how to create your own.