AI memory

Local-first run cache for coding-agent sessions

Six Claude skills for building and maintaining a "context kit" — a CLAUDE.md + structured docs/ tree that gives AI agents durable, low-noise project memory across sessions.

Governed continual-learning memory for AI agents — rejects poisoned facts, derives unstored relationships. Reproducible head-to-head benchmarks.

Cache-optimised architecture and Shadow VFS framework for token-efficient LLM agents.

Lovable-native knowledge accumulation skill (mem:// variant of claude-domain-memory)

Persistent memory for AI agents. Nodedex captures your agent's conversations, extracts the decisions, dead-ends, and reasoning into a causal knowledge graph, and serves it back over MCP at decision time so your agent compounds across sessions instead of resetting every time.

MCP server wrapping semantic-memory — local-first knowledge management with evidence-scored retrieval, contradiction detection, and adaptive routing

Letheo - Cognitive Runtime: agent memory engine (Rust + Python)

Capture non-obvious learnings while coding; auto-recall the relevant ones next time. Plugin for Claude Code & Codex.

Memory-augmented coding agent that remembers code decisions and physical workspace context using Parcle and Afferens.

One shared memory for all your AIs — a local-first, native macOS memory layer (MCP).

Fully local project memory for Claude Code. No API key, no external model, nothing sent anywhere.

memory practice react native app

Causal graph memory for LLMs - flat token cost regardless of session length.

An MCP server that lets Claude Code recall past conversations from any project, as clean compact Markdown.

Verified agents — nothing is "done" until a grader returns a verdict. Eyes (AgentVision) + verdict bus + compounding memory + a fleet + agent-built tooling + agent-run CI/CD.

Recipes for agent-readable, human-readable Markdown brains and lean memory systems

A lightweight memory engine for AI agents using fuzzy graphs, Hebbian updates, and optional LLM gating.

Git-based CLI memory harness for AI agents: structured project memory, flexible wiki, CLI first.

Memory and context engine + app that is extremely fast, scalable, and can be run fully locally. The Memory API for the AI era.