bulhufas

What it is

A single Go binary that captures conversations, extracts structured project artifacts, and makes them searchable by semantic embedding. The vector store and the embedding model are both embedded in the binary, so there is no Ollama, no Docker and no external process.

What you get

• 10 tools once connected: save_conversation, remember, search, recall, observe_turn, list_chunks, update_status, delete_chunk, list_actions, consolidate_memory
• Chunk types that match how project talk actually breaks down — decision, action_item, blocker, requirement, scope_change, context, research_finding, status_update
• recall returns a bounded context packet with memory IDs and source references, so an LLM pulls only what it needs
• Working, episodic, semantic and procedural memory in isolated namespaces, each with provenance, confidence, importance and a validity window
• list_actions for everything still pending, and update_status / delete_chunk so the knowledge base stays current
• An HTTP API on port 8420 as an alternative to MCP stdio, plus a memory proxy for providers that do not speak MCP at all

Requirements

Go 1.22+ with CGO enabled to build from source; then add the binary to your client with --mcp for stdio mode. On first run it downloads the embedding model (all-MiniLM-L6-v2, about 80MB) into ./data/models/. DATA_DIR sets where the SQLite database, model files and vector index live. Automatic consolidation of episodic memory is optional and only runs when MEMORY_LLM_BASE_URL points at an OpenAI-compatible endpoint. It runs on a 2GB VPS.

Setup effort

Build from source — git clone https://github.com/HugoluizMTB/bulhufas.git

Tools you get

10 tools named in the project's documentation. action_item, decision, blocker and similar names are chunk types, not tools; remember, search and recall are the memory tools.

Where it runs

The documented client runs the server on your machine.