AI Dimag — Verified Memory for AI Coding Agents

Your codebase remembers its decisions, conventions, and rules — and proves they're still true.

Documentation • Getting Started • AI Dimag Cloud • Pricing

What is AI Dimag?

AI Dimag is a memory system for software engineering — not a general-purpose "AI memory" app. It gives any MCP-compatible agent (Claude, Cursor, Copilot, Windsurf…) a persistent memory of your codebase that survives across sessions — decisions, conventions, gotchas, failed approaches, guardrails, and reusable skills — stored as falsifiable claims with grounding evidence in .aidimag/ next to your code.

The subject of memory is your repository, not your preferences or chat history. Every capability — evidence, git-hook verification, guardrails, pre-commit checks, path-scoped recall, session scratchpad — exists to serve day-to-day development work.

🎯 The Difference: Claim-and-Verify, Not Store-and-Retrieve

Most memory systems store text and retrieve whatever is similar later — a stored fact is assumed true forever. That's dangerous in a codebase, where a confidently-retrieved stale fact is worse than no memory at all.

Every AI Dimag memory carries evidence (a shell check, an anchored commit, a test) that dim verify re-runs against the current repo — automatically, via git hooks, on every pull, checkout, and rebase. Beliefs that stop being true go STALE instead of silently misleading your AI.

✨ Works with Every AI Tool

• MCP tools (Claude, Cursor, etc.) get real-time memory via the MCP server
• Non-MCP tools (Copilot, Windsurf, etc.) get static context files (.cursorrules, CLAUDE.md, AGENTS.md, etc.)

Install

npm install -g aidimag

Requires Node 22+. Ships two equivalent binaries: dim (short) and aidimag.

🚀 Quick Start

cd your-repo
dim init                    # creates .aidimag/, installs additive git hooks
dim bootstrap               # optional: LLM-survey the repo into a starter memory set
dim review                  # approve what enters memory (nothing is stored unreviewed)

dim remember "All DB access goes through src/db/store.ts" -k INVARIANT -p src/db \
  -e "STATIC_CHECK:grep -rL better-sqlite3 src --include=*.ts"
dim recall db access
dim verify                  # re-run all evidence; stale beliefs get flagged
dim brief                   # session-start briefing: in-scope memory, guardrails, gaps

# For non-MCP tools (Copilot, Cursor without MCP, etc.):
dim generate-context --format all --auto   # creates .cursorrules, CLAUDE.md, AGENTS.md, etc.

🔌 Connect to Your AI Agent (MCP)

Add to your agent config (e.g. .mcp.json for Claude Code):

{
  "mcpServers": {
    "aidimag": {
      "command": "npx",
      "args": ["-y", "aidimag", "mcp"],
      "env": { "AIDIMAG_REPO": "/path/to/your/repo" }
    }
  }
}

MCP Tools get memory_search, memory_propose, context_note (live in-chat fact capture), chat_harvest (live, tool-agnostic session harvesting with server-side secret redaction), memory_critique (a second critic grounded in verified memory), session-start briefings, session-end extraction, and more.

Non-MCP Tools: dim generate-context -f all renders verified memory into .cursorrules, CLAUDE.md, AGENTS.md, .windsurfrules, and .github/copilot-instructions.md (--auto keeps them refreshed).

Hermes Agent: dim hermes install registers aidimag as a native Hermes memory provider — one command, no pip, no venv. A single stdlib-only Python bridge delegates to the MCP server: session briefings are injected into the system prompt, recall is prefetched per turn, and session learnings become review-queue proposals (never silent writes). Then: hermes config set memory.provider aidimag.

✨ Key Features

🛡️ Human-Gated Capture

Commits, PRs, AI-chat transcripts (Claude Code, Codex, Copilot, Cursor), and pasted docs are mined into proposals. Nothing enters memory until you approve it in dim review (auto-triaged best-first, approve all --min-score 0.7 for batches).

✅ Verification Lifecycle

STATIC_CHECK / COMMIT_REF / TEST_RESULT / EXEC_TRACE / HUMAN_ATTESTED evidence. Failing evidence flips memories to STALE and auto-drafts a recovery proposal. Confidence decays without re-confirmation.

🔒 Evidence Trust Gate

Shell-command evidence that arrives via team sync is never executed until you inspect and approve it (dim verify --trust).

🔍 Hybrid Semantic Recall

FTS5 keyword + vector KNN (OpenAI, local Ollama, or AWS Bedrock; auto-detected except Bedrock, which is explicit opt-in; works keyword-only with none).

🚦 Guardrails & Skills

Behavioral rules (never / ask-first / always) and step-by-step procedures, enforced by dim check (pre-commit) and memory_critique.

👥 Team Mode, Self-Hosted

dim serve + dim sync: local-first replicas, device-code login, brain-scoped API keys, hashed credentials, cross-machine verification consensus.

📚 Knowledgebase Inbox

Drop design docs / ADRs / PDFs / DOCX into knowledge/ and they're summarized into reviewed, pinned memories.

📝 Scratchpad & Provenance Audit

dim scratch (and the scratchpad_* MCP tools) hold short-term session notes — TTL-expiring, never synced, never durable memory. dim audit lists memories resting on the weakest ground (agent-authored, evidence-free, stale, or long-unverified) so you can fix them up like a dependency audit for your repo's knowledge.

🎨 Web Dashboard & Extensions

dim ui — run checks, session briefings, bootstrap, harvest, and context generation from the browser — plus VS Code and IntelliJ extensions.

🥊 How It Compares

AI Dimag follows a claim-and-verify model; other memory systems follow store-and-retrieve. The short version:

Full comparison: aidimag.com/comparison

vs. named tools

How aiDimag relates to the memory tools people usually ask about. These solve a different problem (remembering users and conversations); aiDimag remembers your repository and proves its memories are still true:

Chat-memory benchmarks (LoCoMo, LongMemEval, BEAM) score recall over conversation histories, so they don't apply to aiDimag — its memory subject is the repo. Instead aiDimag publishes its own reproducible suite (below), including the metric none of the chat benchmarks measure: does memory notice when the code changes?

📊 Benchmarks

Reproducible performance and quality suites live in benchmark/ (npm run bench, npm run bench:quality). Headline results (Apple M4, Node 24, 10,000-memory brain — full tables at aidimag.com/benchmarks):

📖 Documentation

Full documentation: aidimag.com

🤝 Contributing

Contributions welcome! See CONTRIBUTING.md for dev setup, project principles, and the PR checklist. All participation is governed by our Code of Conduct.

💰 License & Pricing

AI Dimag is open source under the MIT License — free for everyone, any team size, forever. Use it, fork it, embed it.

The entire local-first product is free: CLI, MCP server, verification, guardrails, skills, IDE extensions, local dashboard, and self-hosted team sync (dim serve).

Want team sync without running a server? AI Dimag Cloud is an optional managed sync subscription — that's how the project stays funded and open source. See Pricing.