Graph-MIND (now turnbook): local memory for coding agents without a single model call
Tools & releasesSource:Hacker News
Graph-MIND, renamed turnbook, is a local long-term memory for coding agents: it stores and retrieves without a single model call, using word-for-word lookup. It reports 91.8% on LongMemEval starting from 3.1k tokens per query, and is shared across Claude Code, Codex, Cursor, Copilot CLI, Gemini CLI and OpenCode. A concrete alternative to memories that delegate Retrieval to the model.
Related articles
Costs: local vs API, done with real numbers
How much does local really cost compared to a cloud API? Verified per-token prices, GPU amortization, electricity and the break-even point, calculated with real numbers.
ML agents that run locally: MLExpert and EpochGo on Ollama, zero API costs
MLExpert raises the bar to 35B and a 72.7% medal rate; EpochGo runs three AutoML agents on 16 GB at zero API cost: what works today, the math and the limits.
Nemotron-Parse: NVIDIA's OCR family for reading documents locally
NVIDIA re-released Nemotron Parse (v1.1, v1.2, 2.0) in the same week, on October 20: under 1 billion parameters, page structure included. Local setup with vLLM and the honest limits.
Get the next local-AI briefing
Once a week, the top selection from iaLocale: articles, news and resources on local AI, and more.
After signing up you receive a confirmation email (double opt-in). Without confirmation we send nothing. No spam, we promise.