Local Memory Plugin for AI Coding Agents
NathanWilbanks_ · x · 2026-07-13
A plugin for AI coding agents has just been released on the AGNT marketplace.
Its key design features:
- local-first repo memory
- sparse neural interlinking
- Smart Thalamus routing
- provenance packets
- recommend-only, drift-aware
The original post cites aggressive benchmarks: approximately 90.64% token reduction in full mode and 98.96% in evidence-only mode. The main selling point is 'no cloud, no API keys, pure local efficiency.'
More from coding & agent
- HeyGen adds a media-sourcing skill for coding agents with 75k images and 10k tracks — HeyGen · 2026-07-22
- Agent search bottlenecks are now about variance, not raw latency — rohanpaul_ai · 2026-07-22
- LangSmith adds tracing for Pipecat, LiveKit, OpenAI Realtime, and Gemini Live — LangChain · 2026-07-22
- An MCP server signs every AI agent tool call into a verifiable Merkle chain — Funky_Chicken_22 · 2026-07-22
- Annotated transcript of a Claude Code team interview is now available — trq212 · 2026-07-22
- Claude Code skill uses 10 Markdown rules to make outputs ADHD-friendly — alex_verem · 2026-07-22