Honcho 记忆管理

配置和使用 Honcho 记忆系统与 Hermes 集成

Honcho Memory for Hermes

Honcho provides AI-native cross-session user modeling. It learns who the user is across conversations and gives every Hermes profile its own peer identity while sharing a unified view of the user.

使用场景

安装配置

Cloud (app.honcho.dev)

hermes honcho setup
# select "cloud", paste API key from https://app.honcho.dev

Self-hosted

hermes honcho setup
# select "local", enter base URL (e.g. http://localhost:8000)

See: https://docs.honcho.dev/v3/guides/integrations/hermes#running-honcho-locally-with-hermes

Verify

hermes honcho status    # shows resolved config, connection test, peer info

架构说明

Base Context Injection

When Honcho injects context into the system prompt (in hybrid or context recall modes), it assembles the base context block in this order:

The session summary is generated automatically by Honcho at the start of each turn (when a prior session exists). It gives the model a warm start without replaying full history.

Cold / Warm Prompt Selection

Honcho automatically selects between two prompt strategies:

You do not need to configure this -- it is automatic based on session state.

Peers

Honcho models conversations as interactions between peers. Hermes creates two peers per session:

Observation

Each peer has two observation toggles that control what Honcho learns from:

Default: all four toggles on (full bidirectional observation).

Configure per-peer in honcho.json:

{
  "observation": {
    "user": { "observeMe": true, "observeOthers": true },
    "ai":   { "observeMe": true, "observeOthers": true }
  }
}

Or use the shorthand presets:

Settings changed in the Honcho dashboard are synced back on session init -- server-side config wins over local defaults.

Sessions

Honcho sessions scope where messages and observations land. Strategy options:

Manual override: hermes honcho map my-project-name

Recall Modes

How the agent accesses Honcho memory:

Three Orthogonal Knobs

Honcho's dialectic behavior is controlled by three independent dimensions. Each can be tuned without affecting the others:

Cadence (when)

Controls how often dialectic and context calls happen.

Higher cadence values fire the dialectic LLM less often. dialecticCadence: 2 means the engine fires every other turn. Setting it to 1 fires every turn.

Depth (how many)

Controls how many rounds of dialectic reasoning Honcho performs per query.

dialecticDepth: 2 means Honcho runs two rounds of dialectic synthesis. The first round produces an initial answer; the second refines it.

dialecticDepthLevels lets you set the reasoning level for each round independently:

{
  "dialecticDepth": 3,
  "dialecticDepthLevels": ["low", "medium", "high"]
}

If dialecticDepthLevels is omitted, rounds use proportional levels derived from dialecticReasoningLevel (the base):

This keeps earlier passes cheap while using full depth on the final synthesis.

Depth at session start. The session-start prewarm runs the full configured dialecticDepth in the background before turn 1. A single-pass prewarm on a cold peer often returns thin output — multi-pass depth runs the audit/reconcile cycle before the user ever speaks. Turn 1 consumes the prewarm result directly; if prewarm hasn't landed in time, turn 1 falls back to a synchronous call with a bounded timeout.

Level (how hard)

Controls the intensity of each dialectic reasoning round.

Higher levels produce richer synthesis but cost more tokens on Honcho's backend.

Multi-Profile Setup

Each Hermes profile gets its own Honcho AI peer while sharing the same workspace (user context). This means:

Create a profile with Honcho peer

hermes profile create coder --clone
# creates host block hermes.coder, AI peer "coder", inherits config from default

What --clone does for Honcho:

Backfill existing profiles

hermes honcho sync    # creates host blocks for all profiles that don't have one yet

Per-profile config

Override any setting in the host block:

{
  "hosts": {
    "hermes.coder": {
      "aiPeer": "coder",
      "recallMode": "tools",
      "dialecticDepth": 2,
      "observation": {
        "user": { "observeMe": true, "observeOthers": false },
        "ai": { "observeMe": true, "observeOthers": true }
      }
    }
  }
}

Tools

The agent has 5 bidirectional Honcho tools (hidden in context recall mode):

`honcho_profile`

Read or update a peer card — curated key facts (name, role, preferences, communication style). Pass card: [...] to update; omit to read. No LLM call.

`honcho_search`

Semantic search over stored context for a specific peer. Returns raw excerpts ranked by relevance, no synthesis. Default 800 tokens, max 2000. Good when you need specific past facts to reason over yourself rather than a synthesized answer.

`honcho_context`

Full session context snapshot from Honcho — session summary, peer representation, peer card, and recent messages. No LLM call. Use when you want to see everything Honcho knows about the current session and peer in one shot.

`honcho_reasoning`

Natural language question answered by Honcho's dialectic reasoning engine (LLM call on Honcho's backend). Higher cost, higher quality. Pass reasoning_level to control depth: minimal (fast/cheap) → low → medium → high → max (thorough). Omit to use the configured default (low). Use for synthesized understanding of the user's patterns, goals, or current state.

`honcho_conclude`

Write or delete a persistent conclusion about a peer. Pass conclusion: "..." to create. Pass delete_id: "..." to remove a conclusion (for PII removal — Honcho self-heals incorrect conclusions over time, so deletion is only needed for PII). You MUST pass exactly one of the two.

Bidirectional peer targeting

All 5 tools accept an optional peer parameter:

Examples:

honcho_profile                        # read user's card
honcho_profile peer="ai"              # read AI peer's card
honcho_reasoning query="What does this user care about most?"
honcho_reasoning query="What are my interaction patterns?" peer="ai" reasoning_level="medium"
honcho_conclude conclusion="Prefers terse answers"
honcho_conclude conclusion="I tend to over-explain code" peer="ai"
honcho_conclude delete_id="abc123"    # PII removal

Agent Usage Patterns

Guidelines for Hermes when Honcho memory is active.

On conversation start

1. honcho_profile                  → fast warmup, no LLM cost
2. If context looks thin → honcho_context  (full snapshot, still no LLM)
3. If deep synthesis needed → honcho_reasoning  (LLM call, use sparingly)

Do NOT call honcho_reasoning on every turn. Auto-injection already handles ongoing context refresh. Use the reasoning tool only when you genuinely need synthesized insight the base context doesn't provide.

When the user shares something to remember

honcho_conclude conclusion=""

Good conclusions: "Prefers code examples over prose explanations", "Working on a Rust async project through April 2026"

Bad conclusions: "User said something about Rust" (too vague), "User seems technical" (already in representation)

When the user asks about past context / you need to recall specifics

honcho_search query=""       → fast, no LLM, good for specific facts
honcho_context                       → full snapshot with summary + messages
honcho_reasoning query=""  → synthesized answer, use when search isn't enough

使用场景 `peer: "ai"`

Use AI peer targeting to build and query the agent's own self-knowledge:

When NOT to call tools

In hybrid and context modes, base context (user representation + card + session summary) is auto-injected before every turn. Do not re-fetch what was already injected. Call tools only when:

Cadence awareness

honcho_reasoning on the tool side shares the same cost as auto-injection dialectic. After an explicit tool call, the auto-injection cadence resets — avoiding double-charging the same turn.

Config Reference

Config file: $HERMES_HOME/honcho.json (profile-local) or ~/.honcho/config.json (global).

Key settings

Dialectic settings

Context budget and injection

The contextTokens budget is enforced at injection time. If the session summary + representation + card exceed the budget, Honcho trims the summary first, then the representation, preserving the card. This prevents context blowup in long sessions.

Memory-context sanitization

Honcho sanitizes the memory-context block before injection to prevent prompt injection and malformed content:

This fix addresses edge cases where raw user conclusions containing markup or special characters could corrupt the injected context block.

常见问题

"Honcho not configured"

Run hermes honcho setup. Ensure memory.provider: honcho is in ~/.hermes/config.yaml.

Memory not persisting across sessions

Check hermes honcho status -- verify saveMessages: true and writeFrequency isn't session (which only writes on exit).

Profile not getting its own peer

Use --clone when creating: hermes profile create --clone. For existing profiles: hermes honcho sync.

Observation changes in dashboard not reflected

Observation config is synced from the server on each session init. Start a new session after changing settings in the Honcho UI.

Messages truncated

Messages over messageMaxChars (default 25k) are automatically chunked with [continued] markers. If you're hitting this often, check if tool results or skill content is inflating message size.

Context injection too large

If you see warnings about context budget exceeded, lower contextTokens or reduce dialecticDepth. The session summary is trimmed first when the budget is tight.

Session summary missing

Session summary requires at least one prior turn in the current Honcho session. On cold start (new session, no history), the summary is omitted and Honcho uses the cold-start prompt strategy instead.

CLI Commands