signet-memory-openclaw

<div align="center">

<picture> <source media="(prefers-color-scheme: dark)" srcset="public/Signet-Logo-White.png"> <source media="(prefers-color-scheme: light)" srcset="public/Signet-Logo-Black.png"> <img src="public/Signet-Logo-Black.png" alt="Signet" width="120"> </picture>

Signet AI

Own your agent. Bring it anywhere.

<a href="https://github.com/Signet-AI/signetai/releases"><img src="https://img.shields.io/github/v/release/Signet-AI/signetai?include_prereleases&style=for-the-badge" alt="GitHub release"></a> <a href="https://www.npmjs.com/package/signetai"><img src="https://img.shields.io/npm/v/signetai?style=for-the-badge" alt="npm"></a> <a href="LICENSE"><img src="https://img.shields.io/badge/License-Apache%202.0-blue.svg?style=for-the-badge" alt="Apache-2.0 License"></a> <a href="./docs/BENCHMARKING.md#current-longmemeval-score"><img src="https://img.shields.io/badge/LongMemEval-97.6%25-black?style=for-the-badge" alt="LongMemEval 97.6% answer accuracy"></a>

97.6% average LongMemEval answer accuracy<br /> Local-first context · source-backed recall · repairable memory · portable across agents

Quick start · Why Signet · Benchmarks · Docs · Discord

</div>

---

Models change. Providers change. Harnesses change. The context provided to each should not.

Signet is a local-first memory and context layer for AI agents. It syncs memories, identity files, session transcripts and secrets between all of your favorite harnesses and models.

Why Signet

| Claim | Why it matters | |---|---| | Local-first custody | SQLite, readable workspace files, transcripts, source records, memories, optional identity files, and encrypted secrets live where you control them | | Source-backed recall | Every useful memory can point back to where it came from | | Repairable memory | Inspect, edit, supersede, delete, reclassify, and scope bad context | | Portable across agents | One layer works across Claude Code, Codex, OpenCode, OpenClaw, Gemini CLI, Pi, OMP, Hermes Agent, MCP, SDKs, and apps | | Team deployment primitives | Signet includes scoped agents, visibility, auth policy, retention controls, secrets storage, and audit-friendly APIs | | Proven recall | Signet scores a 97.6% average on LongMemEval, it is one of the only local-first SOTA memory systems in the world. |

Agent memory has never been about just recall quality. Signet is designed for scale, it tracks where context lives, where it came from, who can see it, and how/when it can be forgotten, all in a living ontology on your device.

Quick start (about 5 minutes)

curl -fsSL https://signetai.sh/install.sh | bash
signet setup                         # interactive setup wizard
signet setup --identity-mode off     # memory + secrets without Signet-managed identity
signet status                        # confirm daemon + pipeline health
signet dashboard                     # open memory + retrieval inspector

If you already use Claude Code, OpenCode, OpenClaw, Codex, Gemini CLI, Pi, Oh My Pi, or Hermes Agent, keep your existing harness. Signet installs under it.

Proof in one repair loop

Run this once:

signet remember "Project Atlas deploys only after QA signs off" \
  --tags project-atlas --who user
signet recall "Project Atlas deploy policy" --tags project-atlas --json

Then open the dashboard:

signet dashboard

This is the smallest proof, but it shows the product shape: the memory is local, queryable, tagged, visible in the dashboard, and repairable instead of being trapped behind a hosted recall response.

If recall returns a stale deployment policy, you can edit or delete the memory, run the same recall again, and verify the agent is seeing corrected context before it acts.

In the dashboard, the record is not a black-box snippet:

Memory: Project Atlas deploys only after QA signs off
Tags: project-atlas
Dashboard actions: edit · delete · mark pinned · similar
Daemon lifecycle: modify · forget · recover

How Signet is different

| Alternative | Good for | Where Signet is different | |---|---|---| | Hosted memory APIs | Fast prototypes and managed memory | Signet keeps storage, provenance, ranking policy, repair, deletion, and self-hosting under your control | | Harness-specific plugins | Improving memory inside one agent shell | Signet runs underneath many harnesses, so context survives tool churn | | Vector/RAG memory | Searching notes and documents | Signet keeps transcripts, identity, source records, repair history, and scoped recall | | Lightweight local stores | Simple private persistence | Signet adds provenance, dashboard inspection, team policy, connectors, MCP, SDKs, and daemon APIs |

| Stay hosted if... | Switch to Signet when... | |---|---| | You need the fastest managed API path | Memory has to live in infrastructure you control | | Recall quality is the only contract | Deletion, repair, provenance, and auditability are also part of the contract | | One app owns the memory surface | Multiple agents, harnesses, SDKs, MCP clients, or internal apps need the same context | | Vendor-managed ranking is acceptable | You need to inspect and tune recall policy around your own sources | | You cannot run a daemon or own backups yet | You need an exportable workspace you can inspect, back up, and move |

Operating tradeoff

Signet is infrastructure, not a hosted shortcut. You run a local or self-hosted daemon, choose an embedding provider, back up $SIGNET_WORKSPACE/, and connect your harnesses through hooks, MCP, connectors, or SDKs.

The trade is deliberate: you operate the memory layer, and in return you can inspect, repair, scope, self-host, back up, and move the context your agents depend on.

For a single-developer install, day two is usually signet status, a workspace backup, and rerunning setup when you add or replace an agent harness.

Is Signet right for you?

Use Signet if you want:

• agents that remember across sessions without prompt bootstrapping
• memory your team can inspect, repair, scope, and self-host
• source-backed recall across private docs, repos, conversations, and artifacts
• one memory layer across agent harnesses, MCP clients, SDKs, and custom apps

Signet may be overkill if you only need short-lived chat memory inside a single hosted assistant or a simple vector search endpoint.

Harness support

Signet is not trying to win by being another agent shell. It runs underneath the tools people already use and gives them one owned memory layer.

| Harness | Integration path | Notes | |---|---|---| | Claude Code | Hooks + MCP | Direct /remember and /recall skills | | OpenCode | Plugin + hooks | Runtime plugin with lifecycle support | | OpenClaw | Runtime plugin | Flagship path; hooks available for legacy setups | | Codex | MCP + compatibility hooks | MCP-first integration; plugin bundle when available | | Hermes Agent | Memory provider plugin | memory_*, recall, and remember tools | | Pi | Extension + hooks | Memory commands and agent-callable tools | | Oh My Pi | Managed extension | Lifecycle recall injection through the managed extension | | Gemini CLI | MCP + GEMINI.md sync | On-demand tools plus identity sync |

> Don't see your favorite harness? file an issue and request that it be added!

Memory that holds up

Signet's latest tracked MemoryBench run averages 97.6% LongMemEval answer accuracy under the rules profile.

The benchmark matters because local custody should not mean weak recall. Signet is designed to retrieve the right facts across long-running, multi-session conversations while keeping memory inspectable and repairable.

That profile keeps the benchmark contract strict: memories are ingested through

/api/memory/remember, recalled through /api/memory/recall, and answered from bounded daemon recall results. Search does not call an LLM.

See Benchmarks for the methodology, scoring note, and run workflow.

Install (detailed)

curl -fsSL https://signetai.sh/install.sh | bash
npm install -g signetai
bun add -g signetai
signet setup               # interactive setup wizard

curl, npm, and Bun all install the same compiled Signet binary. The npm and Bun package-manager paths install the signetai wrapper plus a platform native package tarball from the same GitHub release. Install scripts only link the native binary into place; if scripts are disabled, the wrapper resolves the native package directly. They do not install Bun, rebuild Signet, or install daemon dependencies.

Choose one installation method per machine. signet update install preserves the active method, and signet doctor warns when an inactive package-manager wrapper coexists with a direct native install. Duplicate installs are never removed automatically.

Published native binaries currently cover Linux x64, Linux arm64, macOS x64, macOS arm64, and Windows x64. Windows direct installs should use

npm install -g signetai; the old PowerShell install.ps1 path has been removed until a native Windows direct installer ships.

The wizard initializes $SIGNET_WORKSPACE/, configures your harnesses, sets up an embedding provider, creates the database, and starts the daemon.

> Path note: $SIGNET_WORKSPACE means your active Signet workspace path. > Default is ~/.agents, configurable via signet workspace set <path>.

Tell your agent to install it

Paste this to your AI agent:

Install and fully configure Signet AI by following this guide exactly: https://signetai.sh/skill.md

CLI use

signet status              # check daemon health
signet dashboard           # open the web UI

signet remember "prefers bun over npm"
signet recall "coding preferences"

Multi-agent

Multiple named agents share one daemon and database. Each agent gets its own identity directory (~/.agents/agents/<name>/) and configurable memory visibility:

signet agent add alice --memory isolated   # alice sees only her own memories
signet agent add bob --memory shared       # bob sees all global memories
signet agent add ci --memory group --group eng  # ci sees memories from the eng group

signet agent list                          # roster + policies
signet remember "deploy window is Fridays" --agent alice --private
signet recall "deploy window" --agent alice  # scoped to alice's visible memories
signet agent info alice                    # identity files, policy, memory count

Use the secrets subsystem for credentials. Do not store tokens or keys as recallable memories.

OpenClaw users get zero-config routing — session keys like

agent:alice:discord:direct:u123 are parsed automatically; no

agentId header needed.

In harnesses with command-style integrations, skills work directly:

/remember critical: never commit secrets to git
/recall release process

How it works

Signet separates memory into three layers:

workspace / transcripts
  truth layer: raw files, identity docs, source records, session history

semantic memory
  navigation layer: summaries, entities, decisions, constraints, relations

query layer
  retrieval lens: FTS, vector search, graph traversal, scopes, provenance

The record is preserved first. The daemon indexes it, extracts useful structure, and keeps recall bounded and inspectable. The agent gets the right context before the next prompt starts, with a path back to the raw source when the semantic layer is not enough.

After setup, there is no per-session memory ceremony. The pipeline runs in the background and the agent wakes up with its memory intact.

Read more: Why Signet · Architecture · Knowledge Graph · Pipeline

Architecture

Workspace (~/.agents/)
  AGENTS.md, SOUL.md, IDENTITY.md, USER.md, MEMORY.md, transcripts, memory files
  readable source records and agent identity files

CLI (signet)
  setup, knowledge, secrets, skills, hooks, git sync, service mgmt

Daemon (@signet/daemon, localhost:3850)
  |-- HTTP API (memory, retrieval, auth, skills, updates, tooling)
  |-- File Watcher
  |     identity sync, per-agent workspace sync, git auto-commit
  |-- Distillation Layer
  |     extraction -> decision -> graph -> retention
  |-- Retrieval
  |     FTS + vectors + graph traversal -> fusion -> dampening
  |-- Lossless Transcripts
  |     raw session storage -> expand-on-recall join
  |-- Document Worker
  |     ingest -> chunk -> embed -> index
  |-- Ranking + Feedback
  |     bounded candidate ordering, provenance, source-aware scoring
  |-- MCP Server
  |     tool registration, aggregation, blast radius endpoint
  |-- Auth Middleware
  |     local / team / hybrid, RBAC, rate limiting
  |-- Multi-Agent
        roster sync, agent_id scoping, read-policy SQL enforcement

Core (@signet/core)
  types, identity, SQLite storage/query, hybrid search, graph traversal

SDK (@signet/sdk)
  typed client, React hooks, Vercel/OpenAI helpers, plugin-facing primitives

Connectors
  claude-code, opencode, openclaw, codex, gemini, oh-my-pi, pi,
  hermes-agent

Repository map

See Repository Map for package layout, internal surfaces, and ownership boundaries.

Documentation

• Quickstart
• CLI Reference
• Configuration
• Hooks
• Harnesses
• Secrets
• Skills
• Auth
• Dashboard
• SDK
• API Reference
• Knowledge Architecture
• Knowledge Graph
• Benchmarks
• Roadmap
• Repository Map

Research

| Paper / Project | Relevance | |---|---| | Lossless Context Management (Voltropy, 2026) | Hierarchical summarization, guaranteed convergence. Related runtime notes live in lossless-working-memory-runtime.md. | | Recursive Language Models (Zhang et al., 2026) | Active context management. LCM builds on and departs from RLM's approach. | | acpx (OpenClaw) | Agent Client Protocol. Structured agent coordination. | | lossless-claw (Martian Engineering) | LCM reference implementation as an OpenClaw plugin. | | openclaw (OpenClaw) | Agent runtime reference. | | arscontexta | Agentic notetaking patterns. | | ACAN (Hong et al.) | LLM-enhanced memory retrieval for generative agents. | | Kumiho (Park et al., 2026) | Prospective indexing. Hypothetical query generation at write time. Reports 0.565 F1 on the official split and 97.5% on the adversarial subset. |

Development

git clone https://github.com/Signet-AI/signetai.git
cd signetai

bun install
bun run build
bun test
bun run lint

cd platform/daemon && bun run dev     # Daemon dev (watch mode)
cd surfaces/dashboard && bun run dev  # Dashboard dev

Requirements:

• Bun for normal repo development
• Node.js 18+ for Node-targeted package surfaces
• macOS or Linux
• Optional for harness integrations: Claude Code, Codex, OpenCode, OpenClaw,

Gemini CLI, Pi, Oh My Pi, or Hermes Agent

Embeddings (choose one):

• Built-in (recommended) — no extra setup, runs locally via ONNX (nomic-embed-text-v1.5)
• Ollama — alternative local option, requires nomic-embed-text model
• OpenAI — cloud option, requires OPENAI_API_KEY

Contributing

New to open source? Start with Your First PR. For code conventions and project structure, see CONTRIBUTING.md. Open an issue before contributing significant features. Read the AI Policy before submitting AI-assisted work.

Star History

<a href="https://star-history.com/#Signet-AI/signetai&Date"> <picture> <source media="(prefers-color-scheme: dark)" srcset="https://api.star-history.com/svg?repos=Signet-AI/signetai&type=Date&theme=dark" /> <source media="(prefers-color-scheme: light)" srcset="https://api.star-history.com/svg?repos=Signet-AI/signetai&type=Date" /> <img alt="Star history chart for Signet-AI/signetai" src="https://api.star-history.com/svg?repos=Signet-AI/signetai&type=Date" /> </picture> </a>

Contributors

Made with love by...

<a href="https://github.com/NicholaiVogel"><img align="left" hspace="4" src="https://avatars.githubusercontent.com/u/217880623?v=4&s=48" width="48" height="48" alt="NicholaiVogel" title="NicholaiVogel" /></a> <a href="https://github.com/aaf2tbz"><img align="left" hspace="4" src="https://avatars.githubusercontent.com/u/260091788?v=4&s=48" width="48" height="48" alt="aaf2tbz" title="aaf2tbz" /></a> <a href="https://github.com/Ostico"><img align="left" hspace="4" src="https://avatars.githubusercontent.com/u/8008416?v=4&s=48" width="48" height="48" alt="Ostico" title="Ostico" /></a> <a href="https://github.com/BusyBee3333"><img align="left" hspace="4" src="https://avatars.githubusercontent.com/u/241850310?v=4&s=48" width="48" height="48" alt="BusyBee3333" title="BusyBee3333" /></a> <a href="https://github.com/stephenwoska2-cpu"><img align="left" hspace="4" src="https://avatars.githubusercontent.com/u/258141506?v=4&s=48" width="48" height="48" alt="stephenwoska2-cpu" title="stephenwoska2-cpu" /></a> <a href="https://github.com/PatchyToes"><img align="left" hspace="4" src="https://avatars.githubusercontent.com/u/256889430?v=4&s=48" width="48" height="48" alt="PatchyToes" title="PatchyToes" /></a> <a href="https://github.com/ddasgupta4"><img align="left" hspace="4" src="https://avatars.githubusercontent.com/ddasgupta4?v=4&s=48" width="48" height="48" alt="ddasgupta4" title="ddasgupta4" /></a> <a href="https://github.com/LeuciRemi"><img align="left" hspace="4" src="https://avatars.githubusercontent.com/u/44776125?v=4&s=48" width="48" height="48" alt="LeuciRemi" title="LeuciRemi" /></a> <a href="https://github.com/nyashkn"><img align="left" hspace="4" src="https://avatars.githubusercontent.com/u/1158551?v=4&s=48" width="48" height="48" alt="nyashkn" title="nyashkn" /></a> <a href="https://github.com/Alexi5000"><img align="left" hspace="4" src="https://avatars.githubusercontent.com/u/135995822?v=4&s=48" width="48" height="48" alt="Alexi5000" title="Alexi5000" /></a> <a href="https://github.com/dragontvstaff"><img align="left" hspace="4" src="https://avatars.githubusercontent.com/u/279829920?v=4&s=48" width="48" height="48" alt="dragontvstaff" title="dragontvstaff" /></a> <a href="https://github.com/maximhar"><img align="left" hspace="4" src="https://avatars.githubusercontent.com/maximhar?v=4&s=48" width="48" height="48" alt="maximhar" title="maximhar" /></a> <a href="https://github.com/alcar2364"><img align="left" hspace="4" src="https://avatars.githubusercontent.com/alcar2364?v=4&s=48" width="48" height="48" alt="alcar2364" title="alcar2364" /></a> <a href="https://github.com/noamsiegel"><img align="left" hspace="4" src="https://avatars.githubusercontent.com/u/52804845?v=4&s=48" width="48" height="48" alt="noamsiegel" title="noamsiegel" /></a> <a href="https://github.com/lost-orchard"><img align="left" hspace="4" src="https://avatars.githubusercontent.com/lost-orchard?v=4&s=48" width="48" height="48" alt="lost-orchard" title="lost-orchard" /></a> <a href="https://github.com/gpzack"><img align="left" hspace="4" src="https://avatars.githubusercontent.com/u/271398594?v=4&s=48" width="48" height="48" alt="gpzack" title="gpzack" /></a> <a href="https://github.com/Jarvis-ORC-HPS"><img align="left" hspace="4" src="https://avatars.githubusercontent.com/u/273477147?v=4&s=48" width="48" height="48" alt="Jarvis-ORC-HPS" title="Jarvis-ORC-HPS" /></a> <a href="https://github.com/nanookclaw"><img align="left" hspace="4" src="https://avatars.githubusercontent.com/u/258741235?v=4&s=48" width="48" height="48" alt="nanookclaw" title="nanookclaw" /></a> <a href="https://github.com/quannon"><img align="left" hspace="4" src="https://avatars.githubusercontent.com/u/5967?v=4&s=48" width="48" height="48" alt="quannon" title="quannon" /></a> <br clear="left" />

License

Apache-2.0.

---

signetai.sh · docs · spec · discussions · issues