xinchen03/minta

The context quality layer for AI agents.
Your AI remembers. Minta tells you when it remembers wrong — and what it's allowed to claim.

English · 中文 · 日本語

⭐ New (2026-08): open-core v2 — memory engine + research compliance engine + expert domain pack, now with DeepSeek Harness integration (verified).

Why Minta

Every memory system stores more. Minta's job is to make sure what the agent knows is still true — and that it doesn't claim what it hasn't done.

Contents · Why Minta · Quick Start · Features · Open-Core · Benchmarks · DeepSeek Harness · Roadmap

Product UI

The full Minta workspace (Personal Context Layer, V8.3 engine UI). The layers you see — research cockpit, expert infer, memory health — map to the engine tiers below; the open-core dist ships the memory hub UI, and the rest activate through the same API.

Context Hub — "Stop re-onboarding your AI"	Context Draw — 3D knowledge graph + card recall
Context Health — lifecycle dashboard (decay/conflict at a glance)	Inbox — confirm/discard corrections, counter-example review
Skills Library — 50 registered workflows	Research Workspace — projects, evidence, run packages

Three layers, one engine:

L1 Memory governance   →  stale / conflict / redundant / fragile, found not stored
L2 Expert knowledge    →  rules promoted from your corrections, domain-typed
L3 Claim gates         →  the agent cannot claim a stage it never did (math-model
                          / research workflows) — with calibrated confidence

Quick Start

60 seconds. Local-first, no cloud, no API subscription for the open core.

git clone https://github.com/xinchen03/minta.git
cd minta
python -m pip install -r server/requirements.txt
python minta_cli.py start          # API :8772 · Autopilot :18730 · MCP :18721

Or Docker: docker compose up -d. Then connect your agent:

# any MCP-capable editor/agent — Claude Code / Codex / Cursor / dsh
python minta_cli.py connect claude
# DeepSeek Harness: dsh plugin --profile web add @xxinchen/dsh-plugin  (or connect via MCP → docs/dsh-integration.md)

The web UI opens at http://127.0.0.1:8772 — memory health dashboard, 3D knowledge graph, inbox review, expert panels.

Configuration & Keys (first run)

cp .env.example .env    # then edit secrets
python -c "import secrets; print('MINTA_API_KEY=minta_'+secrets.token_hex(32))"  # generate a secure key

Full variable reference, SMTP, CORS, feature flags → docs/configuration.md. Agent integration per editor → docs/mcp-integration.md.

Features

Open-Core: Open Code, Locked Assets

The hosted tiers above are roadmap features — the open core is always a complete, runnable memory system.

Benchmarks

Research first

Minta started as the memory layer of a research workflow — literature notes, manuscript checklists, journal compliance, verdict-gated claim tracking. See runtime/compliance/ and docs/interaction-guide.md.

Companion execution skills (Apache-2.0, separate repo): nature-skills — reading, figures, citations, polishing.

DeepSeek Harness

Verified integration (2026-08): connect Minta as an MCP server in DSH in 2 minutes — see docs/dsh-integration.md for the exact cordis.patch.yml insert. The open-core plugin bundle is published on npm (@xxinchen/dsh-plugin).

Building & contributing

python scripts/build_open_release.py   # sync publish lineage (A-level only)
python -m pytest tests/                # server test suite

We welcome good-first-issue PRs: entity_linker English patterns, richer demo scenarios. More in CONTRIBUTING.md.

Guides

Interaction Guide · Startup Order · DSH Integration · Configuration · User Guide · MCP Integration

Data & Privacy

• Local-first: database, vectors and logs stay on your machine. No telemetry by default.
• Data export / delete: GET /api/user/export-data · DELETE /api/user/delete-data (authenticated).
• Secrets: generated on first run into .minta_api_key (never committed); privileged APIs are off by default unless explicitly configured.
• See SECURITY.md for disclosure policy.

Vision: Where This Is Going

Memory is the easy part; truth is the product. The agent era already has plenty of "remember more" systems. The bottleneck is the opposite — AIs confidently serve stale, contradicted, or unearned claims. Minta's answer is a context quality layer: the memory knows its own health (stale / conflict / redundant / fragile), the expert layer knows its own limits (calibrated coverage), and the claim gates know what was actually done. The long thesis:

• Personal: every AI assistant, every session starts from a context hub that already understands you — stop re-onboarding your AI.
• Team / enterprise: memory, expertise, and compliance checks shared across a research group or a clinical unit — with audit trails and governance reports.
• Vertical: sports-medicine, clinical-triage, and manufacturing expert packs layered on the same engine, tuned by their users' corrections (data flywheel).

Roadmap

• 2026 Q4 — hosted API (full precision, monitoring), sports-medicine domain pack, npm plugin v1 release
• 2027 Q1 — enterprise private deployment + governance audit reports; SME (structure-mapping) engine public
• 2027 — multi-agent shared memory workspaces (team context layers)

Community & Contact

• 🐛 GitHub Issues — bugs, feature requests (we respond fast)
• 💬 GitHub Discussions — questions, RFCs, show-your-work
• 📮 Research contact — papers, collaboration & governance consulting: open an issue tagged research or DM via Discussions. are the publishable signs of this repo's claims; HackerNews/DSH plugin discussions welcome at every release.

Star Us

🔭 If Minta saved you an hour, give it a ★. One click, three seconds — and it tells the next contributor, integrator, and journal reviewer that this experiment deserves their attention.

References & Lineage

Where the ideas come from (and how Minta differs):

License

Apache-2.0. Upstream bundled resources retain their own licenses — see skills/ notes if added later.