Memorix

[Memorix]

Memorix

Local-first shared memory layer for AI coding agents.
One project memory system for Claude Code, Codex, CodeBuddy Code, Cursor, Windsurf, Copilot, Gemini CLI, OpenCode, Grok Build, OpenClaw, Hermes Agent, Oh-my-Pi, Pi, Kiro, Antigravity, Trae, DeepSeek Harness, WorkBuddy, and any MCP-capable agent.

[npm] [monthly downloads] [CI] [license] [stars]

Listed in the official MCP Registry
[View Memorix on MCP Toplist]

Shared Project Memory | MCP | Git Memory | Reasoning Memory | Plugins | Orchestration

Website | Chinese | Install | Capabilities | Agents | Quick Start | Memory Model | memcode | Active Work | Docs

Maintainer status and the current public work boundary live in ACTIVE_WORK.md. It is the repository's single living work tracker.

[Memorix]

Memorix gives the AI coding agents you already use a shared, searchable project memory that survives new chats, IDE switches, terminal sessions, and handoffs. The memory lives under the Git project, not inside one chat window or one tool.

Use Claude Code today, Codex tomorrow, and Cursor in the afternoon. The agent can change; the project memory stays the same.

Use Memorix when you keep re-explaining the same project to a new agent session: the last session already figured something out, another IDE cannot see it, or a design decision is buried in a chat you cannot find anymore.

Memorix is local-first. SQLite is the canonical store. Small projects use the in-process Orama path; larger projects use a persistent SQLite FTS5 candidate index and, when available, an optional local LanceDB semantic shadow index. Both indexes are rebuildable and are never a limit on how many durable memories you can keep. LLM-backed formation and embedding remain optional.

Capabilities

Memorix is more than a memory store. It also installs agent integrations, keeps useful work events, turns commits into project facts, exposes a local control plane, and can coordinate multi-agent work when a task needs it.

[Works with every agent]

Memorix connects through the interfaces each agent already supports: plugin packages, MCP, project rules, hooks, skills, or the bundled terminal agent. memorix setup chooses the right setup for each agent and keeps stdio MCP as the default transport.

_{Works with agents that speak MCP, expose hooks/rules, or support plugin/package entries. One local-first memory layer shared across all of them.}

Integration surfaces:

See Integration Surfaces for the current support matrix and what each generated file means.

Use the same setup command without --global only when you intentionally want repo-local guidance, rules, or hooks in the current Git project.

CLI, MCP, and HTTP are different entry points:

• memorix CLI is the direct command surface for setup, memory search/store, Git Memory, import/export, dashboard, orchestration, diagnostics, and automation.
• memorix serve is the stdio MCP bridge used by IDEs and coding agents. Its default tool profile is micro, so agents see only the compact core tool set.
• memorix background start / memorix serve-http run the HTTP service for a shared endpoint, dashboard, VPS Docker deployment, or multiple clients.

Multi-device store sync is opt-in and separate from HTTP sharing. It never uploads the live SQLite database or WAL files. By default it only relays qualified project-visible observations for the current Git project; personal, agent-targeted, candidate, and ephemeral records stay local. Pass --scope user to include every local project. Set MEMORIX_SYNC_PROVIDER and inspect memorix sync store status --json before the first push.

[Install]

Requirements:

• Node.js >=22.18.0
• Git, because project identity is derived from the real Git root

Install and initialize:

npm install -g memorixmemorix init --global                   # optional defaultsmemorix setup --agent claude --global   # or codex, copilot, cursor, pi, gemini-cli, opencode,                                       # codebuddy, windsurf, kiro, antigravity, trae, openclaw, hermes, omp

memorix init is optional. It creates or updates TOML configuration:

• ~/.memorix/config.toml for global defaults
• <git-root>/memorix.toml for optional project overrides

Legacy memorix.yml, .env, and ~/.memorix/config.json are still read for compatibility, but new setup flows use TOML.

If you want repo-local guidance or hooks for a specific repository, run the same setup command from inside that repo without --global. Codex is the exception: its supported path is the user-level plugin install, so Memorix leaves project .codex configuration alone.

[Quick Start]

Connect an existing agent

Use the setup command first. The global form is the normal one-time install:

memorix setup --agent claude --globalmemorix setup --agent codex --globalmemorix setup --agent copilot --globalmemorix setup --agent cursor --globalmemorix setup --agent pi --globalmemorix setup --agent gemini-cli --globalmemorix setup --agent opencode --globalmemorix setup --agent windsurf --globalmemorix setup --agent kiro --globalmemorix setup --agent antigravity --globalmemorix setup --agent trae --globalmemorix setup --agent openclaw --globalmemorix setup --agent hermes --globalmemorix setup --agent codebuddy --globalmemorix setup --agent omp --globalmemorix setup --agent dsh --globalmemorix setup --agent workbuddy --globalmemorix setup --agent grok --global

What it installs depends on the target agent, but the goal is the same: make Memorix available wherever you open that agent without asking you to wire every repo by hand.

• Claude Code: installs the Memorix plugin package, adds CLAUDE.md guidance, and enables hook capture when you do not pass --noHooks.
• Codex: installs one user-level Memorix plugin with bundled stdio MCP, skills, and lifecycle hooks. It does not write project-local .codex config or change your model, approval, or sandbox settings. When Codex asks, review the plugin hook definition once with /hooks; --noHooks skips automatic capture.
• GitHub Copilot CLI: installs the Copilot plugin package and official Memorix skills.
• Pi: installs the Pi extension/skills package and native MCP config (Pi 1.0+): ~/.pi/agent/mcp.json with --global, or .pi/mcp.json for project setup.
• Cursor: writes Cursor MCP/rules/config entries in the chosen scope.
• Gemini CLI: installs the extension package, GEMINI.md context, hooks, and skills. Antigravity CLI has an official Gemini CLI migration path, but Gemini CLI remains an active standalone target.
• OpenCode: installs the local plugin file, opencode.json, skills, and AGENTS.md guidance.
• Windsurf, Kiro, Trae: write the MCP/rules/hooks files the target supports.
• Antigravity: installs the official plugin package with plugin.json, mcp_config.json, hooks.json, rules, and skills under ~/.gemini/config/plugins/memorix or .agents/plugins/memorix.
• OpenClaw: installs an OpenClaw-compatible bundle with .mcp.json, official skills, and an OpenClaw HOOK.md/handler.ts hook pack.
• Hermes Agent: installs into Hermes home (%LOCALAPPDATA%\hermes on native Windows, ~/.hermes elsewhere, or HERMES_HOME), enables the plugin in config.yaml, registers plugin hooks, slash/CLI commands, skills, and writes MCP config.
• CodeBuddy Code: installs a user-scope local marketplace plugin under ~/.codebuddy/memorix-local with MCP, skills, and hooks. It does not change existing CodeBuddy model, permission, or settings files; CodeBuddy keeps third-party hook approval in its own /hooks flow.
• Oh-my-Pi: installs an omp.extensions package with extension hook events, a memorix command, official skills, and writes MCP config.
• DeepSeek Harness: writes a Memorix @deepseek-ai/dsh-mcp-client row into $DSH_HOME/cordis.patch.yml (default ~/.dsh/cordis.patch.yml), appends guidance to the harness AGENTS.md, and installs official skills under $DSH_HOME/skills. The row follows DSH's own shipped Memorix reference, so tools appear as mcp__memorix__*.
• WorkBuddy: writes a Memorix MCP server row into ~/.workbuddy/mcp.json (or <project>/.workbuddy/mcp.json for project installs) and appends guidance to AGENTS.md. Tools appear as mcp__memorix__*; there is no hooks surface.
• Grok Build: installs native lifecycle hooks under ~/.grok/hooks/memorix.json and guidance in ~/.grok/AGENTS.md. MCP stays host-owned by default; pass --mcp http to write [mcp_servers.memorix] with url = "http://localhost:3211/mcp". Project-local hooks require Grok /hooks-trust, while global hooks are trusted. Set GROK_HOME to use a custom Grok home.

Need a quieter install? Add --noHooks for targets where setup can control hook capture separately from the host's official package entry. It keeps MCP and guidance, but skips Memorix hook capture.

If you intentionally want repo-local guidance or hooks, run the same command inside that repository without --global.

If your agent only needs a manual MCP entry, use stdio:

{  "mcpServers": {    "memorix": {      "command": "memorix",      "args": ["serve"]    }  }}

For an npm-based MCP client or registry tester, use the complete command npx -y memorix serve. The serve argument matters: memorix without arguments opens the bundled memcode terminal agent when run by a human, while MCP clients should start the stdio server explicitly.

For a manually managed Claude Code entry, add "alwaysLoad": true inside the memorix server object. This lets Claude Code expose Memorix tools during print-mode startup; memorix doctor agents --agent claude can detect and repair a missing setting.

HTTP is not required for normal setup. Use it only when you intentionally want a shared background service, dashboard, VPS Docker deployment, or multiple clients using the same endpoint. Local development uses the Node service directly and does not require Docker:

memorix background start

Then point the client at:

http://localhost:3211/mcp

In HTTP mode, agents should bind the active repo explicitly with memorix_session_start(projectRoot=...) when the client can provide the workspace path. Git remains the final source of truth for project identity.

Uninstall

Preview what will be removed:

memorix uninstall --dry-run

Stop the background service and remove hooks:

memorix uninstall --background --hooks

Full cleanup:

memorix uninstall --yes --background --hooks --purge-datanpm uninstall -g memorix

memorix uninstall reports MCP config entries for manual cleanup instead of silently editing every MCP file it finds.

Work from the CLI

memorix --cwd /path/to/repo resume "continue release blocker"memorix checkpoint listmemorix memory search --query "release blocker"memorix memory --help
# Optional: activate one local agent identity for personal/team records and coordination.memorix identity join --agent-type codex --name codex-mainmemorix memory store --text "private investigation note" --visibility personalmemorix task create --description "verify the release package"
# Deliberate durable memory: create a candidate, then review it before it can enter a Workset.memorix memory long-term add --kind procedural --scope user --portability portable --title "Release verification preference" --text "Run focused tests and a packed-package smoke before publishing." --applicability "When publishing an npm package."memorix memory long-term qualify --id <id> --reason "The user explicitly confirmed this preference."memorix memory long-term approve --id <id> --reason "Reviewed for future local projects."
memorix transfer export --format json --out ./.memorix-export.jsonmemorix transfer import --file ./.memorix-export.jsonmemorix reasoning search --query "why sqlite"memorix git-hook --forcememorix ingest log --count 20memorix workbench

The CLI is direct and does not depend on an MCP session. It binds to the current Git project, or to the project supplied with --cwd. Without an active identity it reads, writes, and exports project-visible memory only. Use memorix identity join or memorix identity use --agent-id <id> only when you intentionally need personal/team memory or coordinated task actions; memorix identity clear returns the terminal to project scope. --as <active-agent-id> is the one-command alternative for scripts. Both camelCase and kebab-case flags are accepted.

Manage controlled media

Media is opt-in. An explicit local import is copied into Memorix's local data directory, hashed, and kept outside the Git worktree. It becomes normal memory only when you attach it. Memorix never captures every screenshot or tool output. An asset may be up to the configured media limit (100 MiB by default). Automatic vision analysis is deliberately capped at 20 MiB; a larger image is still kept and can be attached, but Memorix records a clear text fallback instead of sending an oversized payload to a model provider.

memorix media import --path ./architecture.png --jsonmemorix media attach --asset <asset-id> --title "Architecture diagram" --jsonmemorix media list --kind image --jsonmemorix media show --asset <asset-id> --jsonmemorix media remove --asset <asset-id> --force --json
# Controlled derivations: explicit, bounded, and attachable to memory.memorix media derive-pdf --asset <asset-id> --attach --jsonmemorix media derive-audio --asset <asset-id> --attach --json
# Legacy image analysis now uses the same controlled asset lifecycle.memorix ingest image --path ./architecture.png --json

MiniMax image generation is a deliberate CLI operation. Video generation returns a durable job immediately; inspect or cancel that job rather than waiting in an agent request.

# Configure MINIMAX_API_KEY in your user environment or .env, never in Git.memorix media generate image --prompt "A clean system architecture diagram" --json# Image-to-image with a reference image (MiniMax image-01 / image-01-live):memorix media generate image --prompt "Keep the subject, change the background" --image ./reference.png --jsonmemorix media generate video --prompt "A short product walkthrough" --jsonmemorix media status --job <media-job-id> --jsonmemorix media cancel --job <media-job-id> --json

memorix_media is the compact MCP companion in every profile, including micro. It supports import, attach, list, show, PDF/audio derivations, generation, and job status. MCP image and video generation are disabled by default because they may incur provider costs. Set MEMORIX_MCP_MEDIA_GENERATION=1 only after you deliberately want an agent to request billed MiniMax output. The normal OpenRouter text embedding lane is still text-only; media vectors are created only by a provider that explicitly declares support for that modality. Text descriptions and attachments remain a useful ordinary retrieval fallback.

Use the bundled terminal agent

memorix# ormemcode

This opens memcode, a terminal coding agent that uses the same Memorix project memory as your MCP-connected agents.

[Memory Model]

Search is project-scoped by default. scope="global" searches across projects. The search boosts Git Memory for "what changed" questions and reasoning records for "why" questions.

Long-term memory is deliberately not an automatic dump of every note. A source observation, Claim, workflow, session, and code snapshot keep their existing roles. An agent may ask memorix_store to create an additional long-term record; an explicit request auto-qualifies and enters task briefs as a durable anchor, while hook-captured or Git-derived candidates stay pending until qualified. Approval stays an explicit operator review. Use memorix memory long-term approve|archive|supersede to record the evidence-backed lifecycle. Only a manually created or user-confirmed user + portable item may be considered in another local project; project code, Git facts, tests, workflows, sessions, and observations cannot be promoted into portable user memory.

memorix context "..." is the default Memory Autopilot entry. It builds a compact task-lensed brief for agents: bugfix tasks lean toward tests and repros, release tasks lean toward package/changelog/build checks, onboarding tasks lean toward docs and entry points, and stale or unrelated memories stay in warning lanes instead of flooding the prompt. Use --fallback --brief-json when MCP is unavailable and a CLI fallback needs the same bounded brief plus a receipt of what was selected or omitted; --json remains the detailed diagnostic form. A normal new task does not receive an old-session dump. For an explicit continuation, memorix resume "..." adds only the latest useful session summary, up to three readable durable anchors, and at most one recent source-labelled host compact checkpoint. A durable anchor carries a durable:<id> reference, so an agent can expand the full reviewed record through memorix_detail only when needed. Keyword matches stay primary; when no reviewed durable item matches and an embedding provider is configured, Memorix makes one 1.8-second, no-retry semantic fallback for paraphrases or cross-language tasks. A slow or unavailable provider simply leaves the normal keyword-only Workset intact. A checkpoint is lifecycle evidence, not durable memory or a transcript backup. Agents should read the suggested files before trusting stored memory.

[Runtime Modes]

memorix serve defaults to --mode micro (9 tools) to keep MCP tool schemas small for agents. memorix setup writes --mode lite (21 tools) into the installed MCP config so the normal memory, continuity, and session surface is reachable. Use --mode team (29 tools) for coordination tools, or --mode full (48 tools) for advanced and compatibility tools such as checkpoint inspection.

Shortcuts and aliases: memorix search / remember / recent are direct query shortcuts, bg/bs start the background service, hook runs the hook launcher, and memorix config get|path|migrate inspects or migrates config files.

memorix orchestrate uses the current checkout for single-worker runs. When running multiple workers, it creates task worktrees under .worktrees/ and merges successful task branches back. Use --isolated to force worktree isolation for one worker, --no-worktree to disable it, --allow-dirty to run with uncommitted changes, and --no-auto-merge to preserve task worktrees for manual review.

[memcode]

memcode is the terminal coding agent bundled with Memorix. It can read, edit, run commands, resume sessions, switch models, and use /memory commands — all backed by the same project memory as your MCP-connected agents.

Use it when you want a terminal agent with memory already wired in.

one Git project -> one shared Memorix memory pool

See docs/MEMCODE.md for the memcode-specific guide.

[Configuration]

Minimal ~/.memorix/config.toml:

[agent]provider = "openai"model = "gpt-4o"api_key = "..."
[memory.llm]provider = "openai"model = "gpt-4o-mini"api_key = "..."
[embedding]provider = "auto"
[memory]inject = "minimal"formation = "active"

Use [memory.llm] and [embedding] for Memorix memory quality and retrieval. Use [agent] for the model memcode talks to while coding. Keep credentials in global config or environment variables, and do not commit secrets.

For the optional Atlas Cloud memory preset, run memorix init and choose Atlas Cloud, or set provider = "atlascloud" in [memory.llm]. It uses the OpenAI-compatible https://api.atlascloud.ai/v1 endpoint and reads ATLASCLOUD_API_KEY or the explicit MEMORIX_LLM_API_KEY.

For OpenRouter embeddings, use provider = "api", base_url = "https://openrouter.ai/api/v1", and model = "qwen/qwen3-embedding-8b". Memorix accepts OPENROUTER_API_KEY for that embedding endpoint; MEMORIX_EMBEDDING_API_KEY remains the explicit override.

For Requesty, choose Requesty in memorix init or set provider = "requesty" in [memory.llm] (endpoint https://router.requesty.ai/v1, key from REQUESTY_API_KEY or MEMORIX_LLM_API_KEY). Requesty embeddings use provider = "api", base_url = "https://router.requesty.ai/v1", and model = "openai/text-embedding-3-small" with REQUESTY_API_KEY.

For API Route, choose API Route in memorix init or set provider = "apiroute" in [memory.llm]. The preset uses https://global.api-route.com/v1 and deepseek-v4.1-flash, with your own API_ROUTE_API_KEY or MEMORIX_LLM_API_KEY. It is opt-in memory LLM processing; embeddings and memcode's model registry are configured separately. See configuration.

For Cheaper Inference, choose Cheaper Inference in memorix init or set provider = "cheaperinference" in [memory.llm]. The preset uses https://api.cheaperinference.com/v1 and gpt-5.4-mini, with your own CHEAPER_INFERENCE_API_KEY or MEMORIX_LLM_API_KEY. It is opt-in memory LLM processing; embeddings and memcode's model registry are configured separately. See configuration.

For Runcrate, choose Runcrate in memorix init or set provider = "runcrate" in [memory.llm]. The preset uses https://api.runcrate.ai/v1 and the open-weight deepseek-ai/DeepSeek-V4.1-Flash, with your own RUNCRATE_API_KEY or MEMORIX_LLM_API_KEY. It is opt-in memory LLM processing; embeddings and memcode's model registry are configured separately. See configuration.

For controlled MiniMax media generation, set MINIMAX_API_KEY (global) or MINIMAX_CN_API_KEY (China region) in your environment or .env. The media library never stores that key, a signed output URL, or base64 payloads. CLI generation is explicit; MCP generation additionally requires MEMORIX_MCP_MEDIA_GENERATION=1.

[Docker]

Docker is a VPS/hosted HTTP deployment option, not a requirement for local development or stdio MCP:

docker compose up --build -d

Then open:

• dashboard: http://localhost:3211
• MCP: http://localhost:3211/mcp
• health: http://localhost:3211/health

The container must be able to access the repository path passed as projectRoot for project-scoped Git and config behavior.

[SDK]

Use Memorix directly from TypeScript:

import { createMemoryClient } from 'memorix/sdk';
const client = await createMemoryClient({ projectRoot: '/path/to/repo' });
await client.store({  entityName: 'auth-module',  type: 'decision',  title: 'Use JWT for API auth',  narrative: 'Chose JWT because the API is stateless and used by multiple clients.',});
const results = await client.search({ query: 'auth decision' });await client.close();

[Docs]

LLM-friendly summaries: llms.txt and llms-full.txt.

[Development]

git clone https://github.com/AVIDS2/memorix.gitcd memorixnpm installnpm run lintnpm testnpm run build

Community

Desktop and shell integrations built on Memorix:

• omarchy-memorix — a native Omarchy shell bar widget: pool stats, live global search, per-project breakdown, recent memories, and a workbench launcher. Read-only over ~/.memorix/data; no daemons, no telemetry.

Built something on top of Memorix? Open a PR to list it here.

[Acknowledgements]

Memorix draws from the MCP ecosystem and prior memory projects such as mcp-memory-service, MemCP, claude-mem, and Mem0. memcode is based on the Pi coding-agent codebase and adapts its terminal-agent model for the Memorix ecosystem.

[License]

Apache 2.0

Star History

_{Updated automatically from GitHub's privacy-safe star history API. No generated PRs.}