* [Bitterbot v1.4.0](https://github.com/Bitterbot-AI/bitterbot-desktop) – Local-first personal AI with biologically inspired memory, a dream engine, and a P2P skills marketplace.

* [The Agent Guild v0.4.0](https://github.com/mathomhaus/guild) – Provides shared context, memory, and task coordination for AI coding agents via a single Go binary with local SQLite and hybrid keyword/semantic search.

* [Hippo v1.71.0](https://github.com/kitfunso/hippo-memory) – Biologically inspired memory layer for AI agents with decay, consolidation, and cross-tool portability.

* [Sno Station v1.3.0](https://github.com/sno-ai/sno-station) – Claude Code, Codex, OpenClaw, and other agents into a shared, encrypted workstation that enables cross-agent handoff, peer review, and nightly self-improvement.

* [OKF Agent Memory v0.6.0](https://github.com/okf-memory/okf-agent-memory) – A Git-native, domain-neutral persistent memory layer for AI agents using the Open Knowledge Format (OKF) v0.2 with fast local BM25 search and a built-in MCP server.

* [GrayMatter v0.20.0](https://github.com/angelnicolasc/graymatter) – Three-line embeddable agent memory layer providing persistent memory and reducing token usage by about 90%.

* [The Curator v3.81.0](https://github.com/talirezun/the-curator) – Context and working-state wiki that ingests documents into personal or shared markdown knowledge and preserves agent handoffs across sessions, models, and machines via your own GitHub repo.

* [OwnMem v0.8.0](https://github.com/grpcer/ownmem) – Git-native memory that provides deterministic, reviewable local recall for AI coding agents, with evidence and risk gates to prevent harmful memory changes.

* [deja-vu v0.21.0](https://github.com/vshulcz/deja-vu) – Zero-dependency CLI memory layer that indexes Claude Code, Codex, and opencode session logs for fast search, agent recall, redaction, stats, and sync.

* [PrismerCloud v2.2.68](https://github.com/Prismer-AI/PrismerCloud) – Persistent memory, real-time messaging, and an evolution engine for AI agents with one-command self-hosting.

* [Kenfold v0.1.0](https://github.com/jeonjw85/kenfold) – Self-hosted, typed memory server that shares agent decisions and context across multiple AI agents via MCP with provenance, history, and poisoning-aware storage.

* [Mnemon v0.2.10](https://github.com/mnemon-dev/mnemon) – LLM-supervised persistent memory for AI agents with graph-based recall, intent-aware retrieval, importance decay, and automatic deduplication.

* [OpenLore v0.7.3](https://github.com/aakarim/OpenLore) – Minimal, customisable knowledge base serving agent docs over SSH and MCP with identity-scoped access and governed, validated writes.

* [AtomicMemory cli-v0.4.0](https://github.com/atomicstrata/atomicmemory) – Inspectable, portable semantic memory layer for agents and applications, supporting portable capture, groundings, and correction-aware knowledge across SDK, CLI, MCP, adapters, and plugins.

* [dsh-mnemon v0.5.17](https://github.com/omdsh-dev/dsh-mnemon) – Composable, view-based memory for DeepSeek Harness with pluggable sources and strategies and three-tier storage support.

* [ax v0.44.4](https://github.com/Necmttn/ax) – Local agent-experience loop that learns from AI coding agent sessions, records retro experiments in a typed graph, and proposes repo-specific fixes for review.

* [AgentRecall v3.4.50](https://github.com/Goldentrii/AgentRecall-X) – Correction-first agent memory with an MCP server, SDK, and CLI, persisting structured corrections and measuring whether agents stop repeating mistakes across sessions.

* [Utopia v0.1.0-rc9](https://github.com/deeplethe/utopia) – Passively evolving enterprise world model that captures knowledge, rules, reasoning, and controlled execution over time.