Autonomous Memory

English | 中文 When the local memory backend is enabled, the agent automatically extracts durable knowledge from past sessions and injects a compact summary into future sessions for the same project. Over time it builds a project-scoped memory store — technical decisions, recurring workflows, pitfalls — that carries forward without manual effort.

Disabled by default. Enable the local summary pipeline via /settings or config.yml:

memory:
  backend: local

Usage

What gets injected

At session start, if a memory summary exists for the current project, it is injected into the system prompt as a Memory Guidance block. The agent is instructed to:

• Treat memory as heuristic context — useful for process and prior decisions, not authoritative on current repo state.
• Cite the memory artifact path when memory changes the plan, and pair it with current-repo evidence before acting.
• Prefer repo state and user instruction when they conflict with memory; treat conflicting memory as stale.

Reading memory artifacts

The agent can read memory files directly using memory:// URLs with the read tool:

/memory slash command

How it works

Local summary memories are built by a background pipeline that runs at startup; /memory enqueue marks consolidation work that the next startup picks up. The pipeline is skipped for subagents and for sessions that are not persisted to a session file.

Phase 1 — per-session extraction: For each past session that has changed since it was last processed, a model reads the session history and extracts durable signal: technical decisions, constraints, resolved failures, recurring workflows. Sessions that are too recent, too old, currently active, or beyond the configured scan/age limits are skipped. Each extraction produces a raw memory block and a short synopsis for that session.

Phase 2 — consolidation: After extraction, a second model pass reads all per-session extractions and produces three outputs written to disk:

• MEMORY.md — a curated long-term memory document
• memory_summary.md — the compact text injected at session start
• skills/ — reusable procedural playbooks, each in its own subdirectory

Phase 2 uses a lease and heartbeat to prevent double-running when multiple processes start simultaneously. Stale skill directories from prior runs are pruned automatically.

Consolidated output is redacted for common secret/token patterns before MEMORY.md, memory_summary.md, or generated skills are written to disk.

Extraction behavior

Memory extraction and consolidation behavior is driven by static prompt files in packages/coding-agent/src/prompts/memories/.

Model selection

Memory piggybacks on the model role system.

If the requested memory role is not configured, memory model resolution falls back to the default role, then the active session model, then the first model in the registry.

Configuration

Hindsight remote backend

Hindsight requires a reachable Hindsight server. The default endpoint is http://localhost:8888; set a token when the server requires authentication:

memory:
  backend: hindsight
hindsight:
  apiUrl: http://localhost:8888
  apiToken: ${HINDSIGHT_API_TOKEN}

HINDSIGHT_* environment variables override hindsight.* settings, which override built-in defaults. See the complete Hindsight environment-variable table for all 18 supported overrides, accepted values, parsing rules, precedence, and defaults.

By default, Hindsight uses per-project-tagged scoping: writes go to a shared bank with a project tag, while recall includes project-tagged and untagged global memories. per-project isolates each working-directory project in its own bank; global uses one shared bank. An explicit hindsight.bankId selects the bank base. Changes to the bank ID, prefix, or scoping rebuild the primary session state so later operations use the new scope.

Both project-scoped modes name the project the same way: take the repository’s primary checkout root (so every linked worktree of one repository resolves to the same directory), then lowercase its basename. A checkout at ~/code/General therefore tags project:general. Tags are matched literally, so this fold is what keeps one repository in one memory scope no matter how the path is capitalised.

The primary session recalls on its first model turn (hindsight.autoRecall: true) and automatically retains completed conversation turns every three user turns by default. /memory enqueue flushes queued tool retains and forces retention of the current session. At agent end, the primary state schedules cadence-based retention and flushes the retain queue; session disposal drains that queue before releasing the state. Request failures and configured timeouts are logged and leave the coding session usable. Subagents alias the parent’s client, bank, and scope for explicit recall, retain, and reflect calls, but do not run their own automatic recall or retention.

Recall is injected as background context, not instructions, and recalled memory is also available as extra context during compaction. Selecting Hindsight exposes recall, retain, and reflect; memory_edit is not available because upstream Hindsight memories are not edited through this backend. Additional tuning knobs (concurrency, lease durations, token budgets) are available in config for advanced use.

Key files

• packages/coding-agent/src/memories/index.ts — pipeline orchestration, injection, clear/enqueue entry points (the /memory command routes here via packages/coding-agent/src/memory-backend/local-backend.ts)
• packages/coding-agent/src/memories/storage.ts — SQLite-backed job queue and thread registry
• packages/coding-agent/src/prompts/memories/ — memory prompt templates
• packages/coding-agent/src/internal-urls/memory-protocol.ts — memory:// URL handler