Persistent memory plugin for Codex. Obsidian-style knowledge base that survives across sessions
🫛👣 FAVA Trails — Git-native, curated memory for AI agents via MCP. Draft isolation, promotion gate, thought lifecycle hooks, memory curation protocols, supersession chains.
Memory that forgets: a persistent, self-revising belief-state MCP server and Python API for agentic R&D. Uses a hypothesis DAG to auto-prune dead ends and deduce truth without extra probes.
A local-first memory layer for AI agents — turns the files on your machine into bounded, verifiable memory any assistant can query over MCP. On-device, no cloud.
Git-native why next to the code, with a pin check that proves it still matches. Agents retrieve stored why before they edit; hook and CI attest the attachment. Experimental 0.0.2.
Spatial Memory replaces standard cosine-similarity RAG with physics-inspired 8D manifold where memories and beliefs have: Mass — derived from confidence and affective encoding ; Temperature — recency heat that cools over time (Lorentzian decay); and Gravity — `F = T × m / d²` — hot, massive, nearby concepts pull attention
public releases, GitHub Pages site, public docs, installer scripts
5-plane memory for LLM agents: on-disk graph store, retrieval, prompt-ready recall. Measured, not claimed.
To associate your repository with the agentic-memory-architecture topic, visit your repo's landing page and select "manage topics."