Open Source · MIT Licensed
Your AI has
amnesia.
Persistent memory and cognitive context for AI. brain-mcp turns your conversation history into a queryable brain that any MCP client can use.
25 MCP tools · millisecond recall · 100% local · works with Claude, Cursor, Windsurf
25
MCP Tools
<12ms
Context Recovery
100%
Local & Private
MIT
Licensed
“use brain”
Type it in any conversation with Claude, Cursor, or Windsurf. Your AI instantly gains access to your full thinking history — every decision, every open question, every domain.
Before & After
Context lost vs. context recovered in milliseconds.
See It Work
Real tool calls. Real output. Real-time context recovery.
tunnel_state recovers your full context in 12ms. switching_cost quantifies what you'd lose by changing focus.
tunnel_stateLoad your save-state for any domain
what_do_i_thinkSynthesize your views from real conversations
switching_costKnow the cost before you context switch
context injectionAutomatic context injected into every conversation
What It Does
State Recovery
Pick up exactly where you left off in any project. Like loading a saved game — open questions, decisions, stage, all recovered instantly.
Thought Synthesis
Your AI synthesizes what you think from your real conversations. Not what you bookmarked — what you actually said and decided.
Attention Protection
Know the cost of switching contexts before you switch. Catch dropped threads. Surface dormant work you forgot about.
Semantic Search
Find conversations by concept, not keyword. Local embeddings — no API key, no data leaving your machine.
25 MCP Tools
8 cognitive prosthetic tools + 17 generic tools. All exposed via Model Context Protocol.
🧠 Cognitive Prosthetic (8)
tunnel_stateReconstruct your save-state for any domain.
context_recoveryFull re-entry brief for dormant topics.
switching_costQuantified cost of switching between domains.
open_threadsGlobal unfinished business across all domains.
dormant_contextsAlarm for abandoned topics.
trust_dashboardSystem-wide proof the safety net works.
cognitive_patternsWhen and how you think best.
tunnel_historyEngagement meta-view over time.
🔧 Generic (17)
semantic_searchsearch_conversationsunified_searchsearch_summariessearch_docsunfinished_threadswhat_do_i_thinkalignment_checkthinking_trajectorywhat_was_i_thinkingget_conversationconversations_by_datebrain_statsgithub_searchquery_analyticslist_principlesget_principle6 search · 4 synthesis · 3 conversation · 1 GitHub · 1 analytics · 2 meta. Full reference →
How It Compares
| brain-mcp | Mem0 | Letta | |
|---|---|---|---|
| Memory model | Conversation archaeology | Key-value facts | Tiered memory |
| State recovery | ✅ 8 prosthetic tools | ❌ | ❌ |
| Data source | Your existing conversations | Runtime extractions | Agent conversation |
| Runs where | 100% local | Cloud or self-host | Cloud or self-host |
| Domain modeling | ✅ Multi-domain tracking | ❌ | ❌ |
| Context switching | ✅ Switching cost analysis | ❌ | ❌ |
| Protocol | MCP (any client) | REST API | REST API |
| Price | Free (MIT) | Freemium | Freemium |
How It Works
Voice → sessions → parquet → embeddings → LanceDB → 25 MCP tools.
Sessions
Parquet
Embeddings
LanceDB
MCP Server
25 Tools
Why This Exists
Built by someone with ADHD who kept losing their train of thought. Not files — the state of what they were reasoning about.
Open source because this problem isn't unique. Whether you have ADHD or you just come back to a project after a week and spend the first hour re-figuring out what you already knew — brain-mcp is for you.
“After many iterations of trying to place myself in different boxes, I am rather displaying the cognitive prosthetic I built.”
— Mordechai Potash, creator of brain-mcp
Context that survives is context that compounds.
Your AI conversations already contain everything you need. brain-mcp makes it queryable.