Sandbox
590 repos for mes · Claude CodeClear
kapillamba4/
code-memory

MCP server with local vector search for your codebase. Smart indexing, semantic search, Git history — all offline.

49
basicmachines-co/
basic-memory

AI conversations that actually remember. Never re-explain your project to your AI again. Join our Discord: https://discord.gg/tyvKNccgqN

3.9k
remete618/
widemem-ai
remete618/widemem-aiFrameworks & SDKs

Next-gen AI memory layer with importance scoring, temporal decay, hierarchical memory, and YMYL prioritization

49
aayoawoyemi/
Ori-Mnemos

Local-first persistent agentic memory powered by Recursive Memory Harness (RMH). Open source must win.

323
Sahir619/
fable-method

The Fable Workflow: how Claude Fable 5 worked, distilled into skills any model can run, with the eval that keeps it honest. Think / act / prove.

2.3k

Supports GPT Image 2, Seedance & ComfyUI, with a 1,400+ prompt library, carefully crafted hooks and a multi-task orchestration system

1.7k
MaxFreedomPollard/
Compartment

Encrypted, fully offline agentic memory. One click install, GUI w/ memory map, all OS and agents. Superior memory creation, storage and retrieval.

586

Multi-modal Generative Media Skills for AI Agents (Claude Code, Cursor, Gemini CLI). High-quality image, video, and audio generation powered by muapi.ai.

4.3k
rand/
mnemosyne
rand/mnemosyneConnectors

Mnemosyne is a agentic memory and orchestration system designed to provide Claude Code with persistent semantic memory across sessions.

86
codesstar/
loci

Memory Palace for AI — persistent memory, identity, and multi-project orchestration for Claude Code

197
yantrikos/
yantrikdb-server

Cognitive memory database for AI agents — consolidates duplicates, detects contradictions, fades stale memories via temporal decay. Rust, Apache-2.0, ships as library / MCP server / HTTP cluster.

172
silverstein/
minutes

Open-source, local-first Granola/Otter alternative that Claude Code, Codex, Cursor, and any MCP client can query. Meetings, calls, and voice memos transcribed on-device into markdown you own.

1.5k
GeneGulanesJr/
LaPis

💎 LaPis — Local AI memory for coding agents. Persistent SQLite memory for Pi, Claude Code, Hermes & MCP.

44
membranedev/
application-skills

A large set of app-specific Agent Skills for connecting agents to common SaaS tools.

268

106 social media skills for AI agents - strategy, writing, video, design, platform growth, publishing, and analytics. Works with Claude, Cursor, OpenClaw, Hermes & 40+ agents.

76
ourmem/
omem
ourmem/omemConnectors

Shared Memory That Never Forgets — persistent memory for AI agents with Space-based sharing across agents and teams. Plugins for OpenCode, Claude Code, OpenClaw, MCP Server.

173

mentor — a session-insights skill for AI coding agents. This skill reads your local Claude Code and OpenAI Codex history and writes an /insights-style HTML report on how you work: what you build, where you lose time, and concrete fixes. An agent skill for Claude Code, Codex, and any skills-capable agent.

78
Vexa-ai/
vexa
Vexa-ai/vexaConnectors

Open-source meeting transcription API for Google Meet, Microsoft Teams & Zoom. Auto-join bots, real-time WebSocket transcripts, MCP server for AI agents. Self-host or use hosted SaaS.

2.8k
FlowElement-xinliuyuansu/
m_flow

A bio-inspired cognitive memory engine — a new paradigm for Graph RAG.

4.5k
cdeust/
Cortex
cdeust/CortexConnectors

Cross-platform persistent memory MCP for Codex, Gemini CLI, Claude Code, and other local MCP hosts. 36 cited neuroscience mechanisms, local-first SQLite/PostgreSQL, hybrid retrieval, decay-based consolidation, and reproducible benchmarks. Claude adds optional automatic lifecycle hooks.

72

Correction-first persistent memory for AI agents. MCP server + SDK + CLI. Compounds across sessions.

371
joshuaswarren/
remnic

Open-source memory and context for user-aware agents: scoped memory, provenance, retrieval quality, correction, boundaries, evals, and MCP/HTTP access.

198

High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds. 158 languages, sub-ms queries, 99% fewer tokens. Single static binary, zero dependencies.

43k