Install
$ agentstack add mcp-codejunkie99-brain ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
brain
Git-backed long-term memory for AI coding agents.
brain gives Claude Code, Cursor, Codex, OpenClaw, Hermes, and MCP-capable tools one shared local memory. Notes are stored as git commits in ~/.brain, indexed for search, and available through the CLI, TUI, and MCP server.
Follow @Av1dlive on X
Install
Homebrew on macOS installs the prebuilt binary:
brew install codejunkie99/tap/brain
brain onboard
From source:
git clone https://github.com/codejunkie99/brain.git
cd brain
cargo install --path crates/brain-cli
brain onboard
First run
brain onboard
Onboarding creates or keeps ~/.brain, lets you choose which agents to wire, shows the exact files it will write, then asks before saving. It does not create cloud accounts, install daemons, store API keys, or send memory anywhere.
You can type agent names naturally:
claude code
wire claude code and cursor
codex openclaw hermes
all
none
Scripted setup:
brain onboard --agents all --yes
brain onboard --agents claude-code,cursor,codex --yes
brain onboard --agents openclaw,hermes --yes
Refresh managed wiring later:
brain onboard --agents all --yes --reconfigure
Use it
brain note "remember that auth uses PKCE"
brain ask "auth"
brain log
brain tui
brain tui opens the terminal dashboard.
Agent files
When selected during onboarding, brain can write:
| Agent | Files | |---|---| | Claude Code | ~/.claude/mcp_servers.json, ~/.claude/CLAUDE.md | | Cursor | /.cursor/mcp.json, /.cursor/rules/brain.mdc | | Codex | ~/.codex/config.toml, ~/.codex/AGENTS.md | | OpenClaw | ~/.openclaw/workspace/BRAIN.md | | Hermes | /AGENTS.md |
Existing files are not overwritten by default. Managed prompt blocks use BRAIN:START / BRAIN:END markers so re-runs do not duplicate content.
Sync
Sync is explicit:
brain remote add origin
brain push
brain pull
Troubleshooting
brain doctor
brain doctor --deep
Use doctor --deep when search or log output looks inconsistent. It rebuilds the local SQLite index from git without changing the source-of-truth event log.
By default, memory lives in ~/.brain. Override it with BRAIN_DIR or --brain-dir .
Commands
brain onboard
brain note "any text"
brain ask "word"
brain log
brain tui
brain doctor
brain serve --mcp
brain remote add origin
brain push
brain pull
License
Apache-2.0. See [LICENSE](LICENSE).
Source & license
This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: codejunkie99
- Source: codejunkie99/brain
- License: Apache-2.0
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.