The idea
Useful intelligence is cumulative. Memory should be inspectable, portable, and yours.
What it remembers
A graph, not a pile
Memories carry typed edges — caused_by, contradicts, learned_from, depends_on — so recall follows the shape of how decisions actually happened.
Multimodal recall
Text, images, audio, and PDFs share one vector space via gemini-embedding-2. A written cue finds the sketch; spreading activation surfaces the context around it, not just the match.
Lessons that change behavior
A lesson is structured, not sentimental: the trigger to watch for, the wrong default, the better next action, and the evidence. Agents replay them before repeating a mistake.
Cognitive Pulse
A background maintenance runner that notices stale tasks, orphans, and duplicates — then proposes. Review and application stay explicit; your history is never quietly rewritten.
Connect
Point a client at the graph
Works with Claude connectors, ChatGPT developer mode, Claude Code, Cursor, and any client that speaks Streamable HTTP MCP. OAuth and API keys can run side by side.
- MCP endpoint
- https://turbo-brain.com/mcp
- Transport
- Streamable HTTP
- Authorization server
- https://turbo-brain.com
- Scopes
- openid profile email offline_access
- OAuth
- enabled
- API keys
- enabled — Authorization: Bearer or X-API-Key
- Self-host skill
- https://turbo-brain.com/skills/self-host/SKILL.md
- Version
- 0.5.1
Agent first
Install the skill, add the server, and start every relevant task by asking the graph what it already knows.
# 1. Install the agent skill mkdir -p "${CODEX_HOME:-$HOME/.codex}/skills/beautiful-brain" curl -fsSL https://turbo-brain.com/skills/beautiful-brain/SKILL.md \ -o "${CODEX_HOME:-$HOME/.codex}/skills/beautiful-brain/SKILL.md" # 2. Connect the MCP server claude mcp add --transport http beautiful-brain https://turbo-brain.com/mcp # 3. First use Call reflect({ topic: "<project>", goal: "<what you are doing>" }) For repeat work: find_process_patterns({ task: "<task>" })
Self-host with your agent
Want your own instance? Hand the setup to your agent: it fetches the self-host skill and drives the whole install — prerequisites, Docker, config, verification — asking you at most three questions.
Tool surface
memory capture_memory · update_memory · search_memory · recall_memory · get_context · link_memory · reflect skills list_skills · use_skill patterns capture_process_pattern · find_process_patterns collaboration collab_status · share_context · save_share · assign_task · update_assignment connectors search · fetch maintenance run_cognitive_pulse · list_meta_proposals · get_meta_run · apply_meta_proposal · reject_meta_proposal · repair_synapses