Top Tweets for #Gbrain

🚀 We have officially OPEN-SOURCED brain.md! With AI agents (Cursor, Claude Code, Codex) writing code at lightspeed, we face a new bottleneck: Who teaches them your system architecture, historical trade-offs, and tech debt? Code is no longer scarce. The intent behind the code is the ultimate asset. That’s why we created brain.md — an Open Project Brain Standard for AI-native development. 🧠 Local-first. Git-native. 100% Portable. It formalizes project memory into a clean, LLM-consumable Markdown structure that lives directly in your repo. No vendor lock-in. 🔗 Read the Spec: https://t.co/yv0HoXaNq9 Let's give our AI agents a brain to read before they write! 💻🧠 #OpenSource #AINative #GitNative #DeveloperTools #ProjectBrain #MemoryLayer

What actually is GBrain? (Y Combinator CEO's personal agent brain) Every agent memory tool you've seen solves a simple problem: store facts, retrieve facts. GBrain solves a different one. It gives your agent a knowledge system that wires itself, enriches itself, and compounds while you're not even using it. Here's what makes it fundamentally different from Mem0, Zep, LangMem, or a CLAUDE.md file. The standard approach to agent memory is vector-based. Your agent stores memories as embeddings, retrieves them by semantic similarity, and that's the loop. Some tools add a knowledge graph on top. GBrain flips the model entirely. The source of truth is a folder of markdown files. One page per person, one page per company, one page per concept. Every page follows the same two-part structure: 𝗖𝗼𝗺𝗽𝗶𝗹𝗲𝗱 𝘁𝗿𝘂𝘁𝗵 on top: your current best understanding, rewritten as new evidence arrives 𝗧𝗶𝗺𝗲𝗹𝗶𝗻𝗲 on the bottom: an append-only evidence trail that never gets edited This is not a vector store with a markdown export. The markdown IS the system of record. You can open it in VS Code, edit it by hand, and 𝗴𝗯𝗿𝗮𝗶𝗻 𝘀𝘆𝗻𝗰 picks up the changes. Now the part that makes this compound. Every time a page is written, GBrain extracts entity references and creates typed relationship links: 𝘄𝗼𝗿𝗸𝘀_𝗮𝘁, 𝗶𝗻𝘃𝗲𝘀𝘁𝗲𝗱_𝗶𝗻, 𝗳𝗼𝘂𝗻𝗱𝗲𝗱, 𝗮𝘁𝘁𝗲𝗻𝗱𝗲𝗱, 𝗮𝗱𝘃𝗶𝘀𝗲𝘀. All deterministic, all regex-based, zero LLM calls. The knowledge graph wires itself on every single write, without spending tokens. So when you ask "who works at Acme AI?" or "what has Bob invested in this quarter?", the agent walks the graph instead of relying on vector similarity (which struggles with relational queries like these). Search layers ~20 deterministic techniques in concert: intent classification, multi-query expansion, vector search, keyword search, reciprocal rank fusion, cosine re-scoring, compiled-truth boosting, and backlink ranking. Each catches what the others miss. But the real unlock is the compounding loop. GBrain has a 𝘀𝗶𝗴𝗻𝗮𝗹 𝗱𝗲𝘁𝗲𝗰𝘁𝗼𝗿 that fires on every message and captures entities in the background. Person mentioned once? They get a stub page. Three mentions across different sources? Web enrichment kicks in. After a meeting? Full pipeline. The agent runs a 𝗱𝗿𝗲𝗮𝗺 𝗰𝘆𝗰𝗹𝗲 overnight: scans conversations, enriches missing entities, fixes broken citations, consolidates memory. You wake up and the brain is smarter than when you went to bed. This is fundamentally different from memory systems that only store what you explicitly tell them to store. Garry Tan (President and CEO of Y Combinator) built this to run his actual AI agents. It ships with 34 skills, runs on embedded PGLite (no server, ready in 2 seconds), and works as an MCP server for Claude Code, Cursor, and Windsurf. GBrain: https://t.co/11T8Wp95RK