README.md

May 27, 2026 · View on GitHub

Your next AI session should pick up the context you built, not lose it in chat history.

Origin gives AI work one local home: decisions, lessons, gotchas, and project context are captured in flow, distilled into source-backed wiki pages, and brought back as retrieval context across chats, projects, and time.

Agents query the same store through atomic memories, distilled pages, graph context, and hybrid retrieval. You read the Markdown artifacts under ~/.origin/. Same source-backed store, two surfaces.

What makes Origin distinct

Composition, not just storage. Origin does not stop at chat-memory snippets. Captures cluster into source-backed wiki pages, and those pages feed retrieval alongside atomic memories, FTS, vectors, and graph neighbors.
Review before trust. Low-confidence captures and contradictions surface for review when they happen, instead of silently entering context. Supersession chains and protected-memory conflicts stay visible.
Mandatory, refreshable provenance. Wiki pages cite source memory IDs, carry stale_reasons and revision_state, and refresh through /distill or opt-in self-evolving background cycles when you add a local model or API key. The daemon refuses unsourced pages instead of letting hallucinated summaries enter the store.
Real git versioning. Memory, page, and session writes commit into ~/.origin/.git/, so you can inspect, diff, revert, branch, or symlink the Markdown artifacts into Obsidian.
```
a1b2c3d page: embedding-retrieval refreshed (4 sources)
9f8e7d6 session: handoff embedding-work
5a4b3c2 capture: decision mem_abc123
```

Quickstart

Claude Code in 30 seconds

/plugin marketplace add 7xuanlu/origin
/plugin install origin@7xuanlu
/init

If Claude Code asks for a restart after installing, restart once, then run /init. The plugin handles daemon setup, MCP wiring, local memory setup, and the first round-trip check.

Then try /brief, /capture <decision>, or /handoff inside Claude Code.

Plugin details and daily commands: plugin/.

MCP-only setup

Use this if you want Origin tools in Claude Code without the plugin, or in Codex, Cursor, Claude Desktop, VS Code, or Gemini CLI.

npx -y @7xuanlu/origin setup
~/.origin/bin/origin mcp add claude-code      # or: codex, cursor, claude-desktop, vscode, gemini

MCP-only gives agents tools for capture, recall, context, doctor, and page distillation. It does not install Claude Code slash skills like /brief, /handoff, /distill, or /init.

Terminal runtime setup

Set up the local Origin runtime:

npx -y @7xuanlu/origin setup

Then start with ~/.origin/bin/origin status, ~/.origin/bin/origin recall <query>, or ~/.origin/bin/origin store <text>. CLI details: crates/origin-cli.

How Origin works

Origin follows the rhythm of an AI work session, with five verbs you use directly:

Session starts. /brief [topic] loads project status, identity, preferences, and topic-relevant memories so the agent walks in with context.
During work. /capture <thing> saves a decision, lesson, gotcha, or project fact in flow. /recall <query> looks anything up.
Session ends. /handoff writes what changed, what's still open, and where to continue, so the next run picks up cleanly.
Between sessions. The daemon deduplicates overlapping captures and links related ideas in the background. /distill synthesizes wiki pages from clusters of related memories when you want a deliberate pass.
Next session. /brief brings it all back in the Claude Code plugin. MCP-only clients call the context tool for the same underlying memory without replaying full chat history.

Full skill reference: plugin/skills.

No cloud sync or telemetry by default. Local models and Anthropic keys are opt-in for automatic distill cycles.

What you get

Atomic memory layer: every capture is stored first as a typed memory with source agent, confidence, stability, and supersession metadata.
Source-backed pages: pages keep source memory IDs, stale reasons, and revision state so distillation can refresh them without losing provenance.
Hybrid retrieval on libSQL: memories, pages, FTS5 text search, vector embeddings, and graph context live in one local store your MCP clients can query.
Knowledge graph context: people, projects, tools, observations, and relations become retrievable context instead of isolated notes.
Distill cycles: run /distill manually today, or add a local model/API key for background extraction, page refreshes, recaps, and richer graph links.
Background enrichment and decay: post-ingest passes link entities, enrich titles, grow matching pages, and update effective confidence based on memory type, access, and age.
Review before trust: low-confidence captures, pending revisions, protected-memory conflicts, contradictions, and supersession chains can surface instead of silently entering context.
Explicit spaces: tag memories, pages, and recalls with space=work | personal | client-X so a day-job capture never bleeds into a side-project brief. Auto-detected from the current repo or workspace when no space is set; overridable always.
Local artifacts: Markdown pages live in ~/.origin/pages/, session logs and project status live under ~/.origin/sessions/, and ~/.origin/ keeps local git history you can inspect, revert, or symlink into Obsidian.

Multi-bucket workflows

Memories belong to a space — a bucket like origin, career, or ideas. Set the active bucket per shell:

ORIGIN_SPACE=career claude

Or declaratively via ~/.origin/spaces.toml (see plugin/examples/spaces.toml). To manage spaces from the CLI:

origin space list
origin space add ideas --default
origin space show ideas
origin space move scratch career

origin doctor prints the current resolver state so you can see exactly which layer chose the active space.

Evaluation

Hybrid retrieval, transparent eval. BGE-Base-EN-v1.5-Q + FTS5 + Reciprocal Rank Fusion; local BGE-Reranker-V2-M3 cross-encoder rerank is the latest shipped path when enabled. The table below is retrieval-only, not end-to-end answer quality. ~168 tokens per recall query. Eval harness at crates/origin-core/src/eval/. Run it yourself.

Update workflow in docs/eval.

Benchmark	Recall@5	MRR	NDCG@10
LongMemEval (oracle, 500 Q)	93.6%	0.857	0.883
LoCoMo (locomo10)	70.0%	0.647	0.684

Repo Map

Origin is daemon-first. origin-server owns the local database, embeddings, distill cycles, knowledge graph, and HTTP API on 127.0.0.1:7878. The plugin, MCP server, CLI, and local tools are thin clients over that daemon.

Path	What lives there
crates/origin-core	Storage, search, embeddings, distill cycles, graph, pages, export, eval.
crates/origin-server	Local daemon and HTTP API.
crates/origin-mcp	MCP server, tools, npm package.
crates/origin-cli	User CLI for setup, service management, search, recall, store, list, agents, model/key setup, and doctor.
plugin/	Claude Code plugin (`plugin.json`, skills, hooks, `.mcp.json`).
docs/eval	Benchmark workflow and methodology.

Full contributor map: CLAUDE.md.

Build from source

Origin builds natively on macOS (Apple Silicon + Intel), Linux (x86_64 + ARM64; glibc), and Windows (x86_64). The npm wrapper (@7xuanlu/origin, origin-mcp) and install.sh auto-detect your platform and pull the matching prebuilt release. Most users should install through the Claude Code plugin or npx. For local development:

git clone https://github.com/7xuanlu/origin.git
cd origin
cargo build --workspace
cargo run -p origin-server

Build details for the daemon, MCP server, CLI, and core crates live in the crate READMEs linked above. Cross-platform specifics (service registration, paths, Windows install limitation) live in AGENTS.md.

Learn more

Longer-form writing on AI work memory and how Origin compares lives at useorigin.app/learn:

Concepts

What is AI work memory? — the shape of the problem Origin solves
MCP memory server — how Origin exposes memory through the Model Context Protocol
Local-first AI memory — data, privacy, and control
Markdown + local index — the storage model
AI agent handoff loop — session-end discipline that prevents context loss

Comparisons

Origin vs Basic Memory — Markdown knowledge base vs AI work-session memory
Origin vs claude-mem — observer-style Claude Code memory vs MCP-first cross-tool memory
Origin vs Superlocal Memory — includes the honest LoCoMo benchmark concession

Docs

Get started — install + verify the first local memory loop
Daily workflow — capture, handoff, distill
MCP clients — connect Claude Code, Cursor, Codex, Claude Desktop, Gemini CLI

What Origin is NOT

Not a Life OS. No habits, calendar, journal, or life-management modules. Origin scopes to AI work artifacts only. If you want a full personal OS, look at PAI.
Not a workflow suite. ~30 MCP tools across one daemon. If you want 30+ skills, 8+ agents, and an auto-research loop bundled, look at pro-workflow. Origin trades breadth for focus.
Not a memory infrastructure SDK. For people using AI daily, not as a backend for other apps building memory features.
Not for one-off chats. Best when work spans sessions, projects, and weeks.

Karpathy's LLM-wiki note. Raw-to-wiki distillation pattern.
Claude Code's MEMORY.md. The simplest version of the idea.

Peers:

agentmemory. Agent-side memory framework.
basic-memory. Local-first knowledge management for Claude.
pro-workflow. Claude Code productivity suite.
mcp-memory-service. Memory service for MCP.
Memoria. "Git for AI Agent Memory" via Copy-on-Write.
OpenMemory, claude-memory-compiler, PAI, Palinode. Adjacent shapes.

Different shapes of the same problem. Try the one that fits.