#agent-memory

Local-first checkpoints and crystals for long-running AI coding agent sessions.

RSS for state. Open portable evidence layer for machine state - preserving what an agent or system saw, produced, derived and learned, so another party or future agent can verify the lineage independently.

No repository description published.

Persistent memory for pi — learns corrections, preferences, and patterns from sessions

A framework for giving any AI agent persistent, browser-trainable SSM memory — Mamba models, swappable LLM bridges, and online distillation. The hippocampus behind BuilderForce.ai.

Mnemoteca — local memory for every agent

Self-improving context & memory for Claude Code and OpenAI Codex. One canonical knowledge store injected only when relevant — hooks push budgeted context, an MCP server serves depth on demand, and it learns lessons from your sessions. Agent memory + context engineering as a single static Go binary.

Call dibs on files. Coordination for parallel coding agents — file claims with expiry, enforcement hooks, and git-native lessons. One binary, no server, no database.

A verifiable memory layer for language models — facts in a graph, every claim with its source.

Python SDK for Niadra: shared customer memory for every AI agent in a company. Context before the model call, history, tools and MCP.

Claude Code plugin marketplace: the bitranox skill collection (82 skills) plus a self-improve Stop hook. Skills invoke as /bitranox:<skill>.

The Context Graph Protocol is an open wire protocol for context retrieval. It treats a piece of context as a typed, budgeted, provenance-carrying, consent-gated, and conformance-verified unit of exchange called a frame — never a blob.

File-first memory runtime for AI agents — versioned, portable, and always there when the next session starts.

Structural memory for AI coding agents. Bi-temporal graph, MCP-native, zero LLM calls. Cursor · Claude Code · Codex · DeepSeek Harness · Hermes · VS Code · Windsurf.

No repository description published.

Membase SDK: drop-in memory infrastructure for AI agents and apps — Python client, CLI, MCP server and TypeScript client, hosted or on your machine.

A tiny, universal memory engine for humans and AI agents — CLI, HTTP API, MCP server, and shared memory hub in one small Go binary

Local-first control plane for AI-agent teams — orchestrates Claude Code, Codex, Grok, agy & Hermes into gated workflows that fix their own failures, with per-run metering, an append-only audit log, and team memory. Apache-2.0.

Vector Graph RAG for code & docs with Persistent Chat-Session Memory — BM25 (multi-lang), AST chunking. Hybrid, Compute, Scan, Timeline, Absence, Salience. Graph + temporal knowledge. Privacy Stamps. Source Adapters. Chat summarisation + verbatim copy + free scan. Git indexing. CLI, MCP and Claude Code plugin. Ollama or cloud LLMs. Dashboard.

No repository description published.

Turn docs into agent-readable knowledge bundles using Open Knowledge Format (OKF)

A living local memory layer for your AI tools.

RAMR — Retrieval-Augmented Memory Reliability: a contamination-resistant synthetic benchmark for agentic-RAG / memory systems (findings + method)

One workflow framework, every coding agent. Install your AI-coding discipline into Claude Code, Cursor, GitHub Copilot, Gemini CLI, Codex, and Windsurf from one tool-agnostic core. Apache 2.0.

Open-source agent middleware — shared memory, credential isolation, and schema learning for AI agents. What one agent learns, every agent knows.

go vet for file-based AI agent state: integrity checks for memory, instructions, decisions, and contracts

A fractal memory plugin and mcp server for opencode.

A small, nestable agent-loop job primitive: loop(body→until→review) composed with dag, pluggable engines, agent-judge gates, budget + run records. TypeScript.

Pi package for reviewed behavioral experience patterns separate from skills and memory

Embedded long-term memory database for AI agents & LLM apps. Six-layer cognitive architecture, knowledge graph, hybrid BM25 + vector search, sleep-time memory consolidation. One .meh file, zero infrastructure, pure Go.