OriMem
Uses an Obsidian vault as the source-of-truth memory store, indexing Markdown notes for hybrid recall and writing verified notes and captured conversation transcripts into vault folders.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
OriMem
Long-term memory for coding agents, kept in your own Obsidian vault.
One local MCP server and one skill, shared by Claude Code, Codex and DeepSeek Harness — recall project context across sessions, write confirmed results back with receipts, and capture every conversation automatically.
English · 简体中文
Why OriMem
Coding agents forget everything when a session ends, and each agent keeps its history in its own private format. OriMem gives them one shared, human-readable memory:
🗂️ Your vault is the memory. Plain Markdown in an Obsidian vault you can read, edit and back up. The index is just a cache.
🔎 Hybrid recall. Multilingual E5 embeddings + SQLite FTS5 + wiki-links. Short snippets first, exact evidence on demand, so context stays small.
✅ Verified write-back.
prepare_record → diff → commit_recordwith hash checks, backups, read-back and receipts. It never silently overwrites a note you edited.🎙️ Automatic capture. Hooks save each Claude Code / Codex / dsh session as a transcript note when a turn ends. Tool output, reasoning, injected system context, sub-agents and automations are left out.
📅 Daily summary (opt-in). The agent asks you once; if you agree, a scheduled job writes the day's journal through the same verified writer.
🔒 Local only. No cloud calls, no telemetry. The embedding model is pinned and checksum-verified, and runs on CPU through ONNX Runtime (no PyTorch needed).
Related MCP server: Conectica
Quick start
Windows (PowerShell)
irm https://raw.githubusercontent.com/Wen5555/OriMem/main/scripts/install.ps1 | iexmacOS / Linux
curl -LsSf https://raw.githubusercontent.com/Wen5555/OriMem/main/scripts/install.sh | shThe installer sets up uv if needed, installs OriMem into an isolated environment (about 120 MB, Python provided by uv), then runs orimem init. init asks three questions — vault path, conversation capture (default on), daily summary (default "ask me later") — downloads the 470 MB embedding model, and connects every agent it finds. Restart your agents afterwards.
Then just talk to your agent:
"What did we decide about the export feature last week?" "Record that the WebGPU renderer is done and the next step is drag-to-reorder layers."
uv tool install git+https://github.com/Wen5555/OriMem.gitpipx install git+https://github.com/Wen5555/OriMem.gitorimem initNon-interactive: orimem init --yes --vault ~/Notes --agents claude,codex. Behind a slow network, the installer switches to mirrors automatically when PyPI is unreachable (ORIMEM_MIRROR=cn forces it).
Supported agents
Agent | MCP server | Skill | Hooks (capture on turn end) | Transcripts read from |
Claude Code |
|
|
|
|
Codex |
|
|
|
|
DeepSeek Harness (dsh) |
|
|
|
|
Any other MCP client |
| copy the skill folder | — | — |
Claude Code users can also install it as a plugin (MCP server, skill and hooks in one step; still needs the orimem command):
/plugin install orimem --marketplace Wen5555/OriMemOn older Claude Code versions: /plugin marketplace add Wen5555/OriMem, then /plugin install orimem@orimem.
DeepSeek Harness users can also add the dsh-orimem bundle from the community plugin market (or dsh plugin --profile <name> add dsh-orimem-<version>.tgz from a release); it needs the orimem command from the quick start.
orimem install and orimem uninstall only add or remove OriMem's own entries, and every edited file is backed up first. Marker blocks in TOML/YAML files are removed byte for byte; JSON files keep all other content.
How it works
flowchart LR
subgraph Agents
CC[Claude Code]
CX[Codex]
DS[DeepSeek Harness]
end
CC & CX & DS -- "MCP (stdio)" --> M[orimem mcp]
CC & CX & DS -. "Stop hook" .-> H[orimem hook]
M --> S[(local service<br/>loopback only)]
H -- "capture this session" --> S
S --> I[(SQLite: chunks · E5 vectors<br/>FTS5 · links · ledger)]
S <--> V[/"Obsidian vault<br/>(Markdown = source of truth)"/]
S -- "every 2 min" --> T[agent transcripts]Recall:
task_contextbinds the current project;recallreturns ranked snippets;evidencefetches exact source text with offsets and hashes.Write-back: the agent proposes a complete note change; OriMem checks the expected hash, backs up, writes, re-reads, verifies the claimed text and issues a receipt.
Capture: per-agent parsers mirror ordinary user/assistant turns into one pipeline, which stages them and projects stable transcript notes under
90 归档/Codex佐证/. Hooks hand the work to the running service (falling back to a detached capture process), so they also work inside sandboxed hook runners such as dsh's.
Configuration
Settings live in ~/.orimem/config.toml. Change them with orimem config set <key> <value> or ask your agent, which uses the config_set tool.
Key | Default | Meaning |
|
| Obsidian vault path |
|
| Capture conversations into the vault |
|
| Which agents to capture |
| install time | Older sessions are not back-filled ( |
|
| Never capture sessions started in these folders |
|
|
|
|
| When the daily job runs |
| auto |
|
| auto | Model download endpoint (falls back to hf-mirror.com) |
Reference
Command | What it does |
| First-time setup |
| Connect or disconnect agents |
| Check config, model, embedder, dependencies and agents |
| Capture now |
| Index / search from the shell |
| Daily summary |
| Embedding model |
| Settings |
| MCP JSON + AGENTS.md snippet for other clients |
| Use another data directory (written into generated agent commands) |
Tool | Purpose |
| Bind the current folder/task to a project entry |
| Hybrid search (snippets) |
| Exact source text for result ids |
| Browse captured conversations |
| Verified write-back |
| Create a project/course entry |
| Source reading, candidates, corrections |
| Maintenance |
| Settings and capture |
00 收件箱/ inbox and knowledge candidates
10 项目/ one page per project (status, next action)
15 课程/ courses
30 知识/ reusable knowledge
50 日记/ 每日/ (daily) · 每周/ (weekly)
90 归档/ archive; 90 归档/Codex佐证/ holds captured transcripts
95 AI 工作区/ agent work notesWrites are limited to layout.folders. .obsidian and files outside the vault are never read or modified.
FAQ
Do I need a GPU or PyTorch? No. Embeddings run on CPU through ONNX Runtime. orimem[torch] plus orimem model download --torch enables the optional PyTorch backend, which produces identical vectors.
Can I use my existing vault? Yes. Point vault at it. OriMem only adds the folders it needs and never rewrites existing notes outside the verified write-back flow.
I'm in mainland China. Both installers detect an unreachable PyPI and switch to the Tsinghua PyPI mirror, the npmmirror Python builds and hf-mirror.com.
How do I turn capture off for a project? orimem config set capture.exclude_cwd '["D:/work/secret"]'. To turn it off everywhere: orimem config set capture.enabled false.
How do I remove everything? orimem uninstall, then uv tool uninstall orimem. Your vault and ~/.orimem stay until you delete them.
Roadmap
PyPI release (
uvx orimem)Configurable / English vault layout
More agents (Cursor, Gemini CLI, OpenCode)
Optional quantized ONNX model for low-memory machines
Contributing
git clone https://github.com/Wen5555/OriMem && cd OriMemuv venv && uv pip install -e ".[test]"uv run pytestA manual end-to-end checklist for each agent is in docs/TESTING.md. Issues and pull requests are welcome.
License
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
An MCP memory server. One memory your agents share — across models, devices and apps.
One memory, every AI. A shared, user-owned markdown memory your AI clients read and write over MCP.
Hosted MCP memory for coding agents: persistent across sessions, editable markdown, team sharing.
Persistent memory, knowledge graph, task management and more for AI agents via MCP.
Related MCP Servers
- AlicenseAqualityBmaintenanceMCP server that exposes a local Obsidian vault as persistent, searchable memory for AI agents, with hybrid retrieval, reranker, and PDF support.34638 npm36MIT
- -licenseNot gradedqualityNot gradedmaintenanceAn MCP server that enables multiple AI models (Claude, ChatGPT, Gemini) to share and persist context via a local-first vault of markdown files and SQLite index, allowing seamless cross-AI memory.-
- AlicenseNot gradedqualityCmaintenanceAn MCP server that provides controlled read/write tools for managing local-first research memory in an Obsidian vault, enabling AI agents to maintain project context across sessions.5 npm1MIT
- AlicenseAqualityCmaintenanceA self-hosted MCP server that gives AI agents shared, long-term memory over a git-backed folder of markdown, enabling persistent knowledge search, read, and write without a database.1624 npm21MIT