Tlamatini – Local-first AI dev assistant with 68 agents and hybrid RAG
Tlamatini is a locally-deployed AI developer assistant designed to enhance coding workflows. It features a hybrid RAG pipeline and a visual workflow designer with 68 drag-and-drop agents. The latest version introduces a new STM32er agent for firmware management, emphasizing local execution and security.
- ▪Tlamatini operates with a hybrid RAG pipeline that includes FAISS and BM25 for metadata extraction.
- ▪The assistant allows for local execution of workflows, ensuring sensitive code remains on the user's machine.
- ▪Version 1.9.0 introduces the STM32er agent, which simplifies STM32 firmware management with zero-config auto-bootstrap.
Opening excerpt (first ~120 words) tap to expand
Tlamatini "one who knows" — a locally-deployed AI developer assistant Tlamatini (Nahuatl for "one who knows") is a locally-deployed AI developer assistant that pairs a hybrid RAG pipeline (FAISS + BM25, metadata extraction, context budgeting) with a Multi-Turn tool-orchestration layer, ACPX delegation to external coding-agent CLIs (Claude Code, Cursor, Codex, Gemini, Qwen, …), and a visual workflow designer with 68 drag-and-drop agents. Local-first by default: the full RAG pipeline, the Multi-Turn execution loop, and every workflow agent run on your machine — embeddings and chat are driven by your local Ollama install. Cloud LLMs (Claude API, Ollama Pro/Max) and ACPX delegation to cloud CLIs are opt-in per-request, never the default.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at GitHub.