neuralmind 3.0.0

Persistent memory for AI coding agents. Your agent learns your codebase the way a senior engineer would — what files go together, what you usually edit next, what patterns matter. Works with Claude Code, Cursor, Cline, Continue, and any MCP-compatible agent. 100% local. Side effect: 12-50× cheaper code questions.

🧠 NeuralMind

Persistent memory and context compression for AI coding agents. Your agent learns your codebase the way a senior engineer would — what goes together, what you usually touch next — and remembers it across sessions. 100% local, no telemetry. Side effect: 12–50× cheaper code questions, measured in CI on every commit.

After install, your agent:

• Boots with SYNAPSE_MEMORY.md (learned associations, strongest hub files)
• Receives PostToolUse compression automatically (Bash output → errors + signals)
• Queries your codebase in ~800 tokens instead of ~50,000

Works out of the box with Claude Code, Codex, Cursor, and Cline. Any other MCP agent: neuralmind install-mcp --all

Website: neuralmind.uk · Docs: docs.neuralmind.uk · Changelog: CHANGELOG.md · Release notes: docs/releases/

---

⚡ 30-second proof — see the memory work

The clearest evidence the memory is working is the measurable side effect: the agent stops re-loading context it already understood. Reproduce it on a fresh clone:

git clone https://github.com/dfrostar/neuralmind && cd neuralmind
bash scripts/demo.sh

The script creates an isolated venv, installs the deps, builds the index for the bundled fixture project, and runs three real questions. Output looks like:

  Q: How does authentication work in this codebase?
     naive = 4,736 tok   neuralmind =  829 tok   reduction =   5.7×

  Average reduction:   5.5×  across 3 queries
  Avg context size:    859 tokens  (vs 4,736 naive)

The fixture is intentionally tiny (~500 lines) — it runs in CI as a regression gate. Real repos measure 12–50× on the same pipeline (benchmarks · measured production results). Then get your own number:

pip install neuralmind
cd /path/to/your-repo
neuralmind build .
neuralmind benchmark .

---

🚀 Quick start

Method	Command
pip	pip install neuralmind
pipx	pipx install neuralmind (global CLI, no env pollution)
uv	uv pip install neuralmind
Docker	docker pull ghcr.io/dfrostar/neuralmind:latest (multi-arch, published on every release)
Source	git clone https://github.com/dfrostar/neuralmind && pip install -e .

No external tools required — a built-in tree-sitter backend indexes Python, TypeScript, Go, Rust, Java, C, C++, C#, Ruby, and PHP out of the box, and the default index is ChromaDB-free (smaller deps, 8–16× smaller index, same answer quality). Full path-by-path walkthrough: install paths.

cd your-project
neuralmind build .          # index the codebase (tree-sitter, ~seconds to minutes)

neuralmind wakeup .         # what the agent sees at session start
neuralmind query . "How does authentication work?"
neuralmind impact MyClass --depth 2   # blast radius: callers, importers, subclasses

neuralmind install-hooks .  # Claude Code: automatic PostToolUse compression
neuralmind serve .          # Obsidian-style graph view in your browser
neuralmind savings . --cost # measured token savings, priced for your model
neuralmind doctor           # verify the install end to end

---

🧠 What you get

• Progressive context disclosure (L0–L3). A question costs ~800 tokens, not your whole repo. The agent asks for more depth only where it needs it.
• A synapse layer that learns. Hebbian co-activation strengthens edges between code that's used together; unused edges decay. Recall is spreading activation over that graph — your agent's context gets better the more you work.
• Session memory. SYNAPSE_MEMORY.md is exported for Claude Code so every session boots already knowing the hub files and learned associations.
• Tool-output compression + recovery. PostToolUse hooks compress noisy Bash output to errors + signals, and a recovery cache brings back tool output the context window dropped.
• Team memory. neuralmind memory publish commits a learned-weights bundle (no source code) that teammates' agents inherit on their next session — a fresh clone starts with the team's earned intuition.
• MCP server for any agent. Claude Code, Codex, Cursor, Cline, Continue, or anything MCP-compatible: neuralmind install-mcp --all.
• Graph view. neuralmind serve renders the index as a force-directed, community-coloured graph with the synapse overlay — backlinks, semantic quick-switcher, clickable neighbours. There's also a VS Code extension.
• Team tier ($29/user/mo). Governance, append-only hash-chained audit log, seat management, self-hosted deployment. MIT core stays MIT — the Team tier only activates with a license; tier2 and Agent OS are source-available, not MIT — see LICENSING.md. See pricing.

How it works under the hood: Architecture · brain-like learning.

---

📊 Benchmarks

Measured, not marketed — the numbers are produced by CI on every commit (every merged PR carries a sticky benchmark comment) and reproduce locally with python -m tests.benchmark.run:

• 100% gold-file recall at 38–85× fewer tokens on the public benchmark.
• Synapse recall A/B: +11 points top-k hit rate at ±0 token cost.
• Real production rebuild: 48.8× average reduction, 1,033 tokens/query (full field report).
• Backend parity gate: the built-in tree-sitter backend is held within tolerance of the legacy graphify backend on every PR.

Methodology, gold sets, and community submissions: benchmarks/ · public methodology.

---

🔒 Security & Compliance

• 100% local engine. NeuralMind makes zero network calls of its own and ships no telemetry. Only the minimal relevant slice of code ever reaches your AI tool.
• CycloneDX SBOM per release, hash-chained audit log (Team tier), signed licenses (Ed25519), tarball integrity instructions on every release.
• Live posture page: neuralmind.uk/security · Policy: SECURITY.md · Compliance summary · SDLC policy

Behavior toggles: NEURALMIND_BYPASS=1 (skip compression), NEURALMIND_SYNAPSE_INJECT=0 (skip prompt-time recall), NEURALMIND_SYNAPSE_EXPORT=0 (skip memory export), NEURALMIND_TEAM_MEMORY=0 (skip team-bundle import). All fail-open.

---

📚 Documentation

I want to…	Read
Install and set up	Setup guide · Installation
See every command	CLI reference
Wire up my agent (MCP)	Usage · wiki Home
Understand the design	Architecture · Limits & failure modes
Follow real workflows	Use-case walkthroughs (20+)
Compare with alternatives	Comparisons
	Evaluate for a team
	Run on multiple codebases
	Upgrade safely
See what changed	CHANGELOG · release notes · ROADMAP

---

❓ FAQ

How is this different from RAG? RAG retrieves similar text. NeuralMind maintains a weighted graph of your code and learns from use — retrieval is spreading activation over structural edges plus Hebbian synapses, disclosed progressively so the agent pays only for the depth it needs.

Does my code leave my machine? No. The engine is fully local. Your agent still talks to its own model — NeuralMind just makes what it sends smaller.

What if it doesn't help on my repo? Run neuralmind benchmark . and read the number. If it's not worth it, uninstall — and see the use cases for guidance on when NeuralMind is the right fit.

Is the paid tier required? No. The core is MIT and complete. The Team tier adds governance, audit, and seat management for organizations.

---

🤝 Contributing

Contributions welcome — see CONTRIBUTING.md, CODE_OF_CONDUCT.md, and SUPPORT.md. Tests live in tests/; pytest tests/ must pass (the synapse layer's tests are stdlib-only). Security reports: see SECURITY.md.

📄 License

MIT for the core — see LICENSE. The optional Team tier is licensed separately — see LICENSE-COMMERCIAL.md.