Sandbox
205 repos for graphClear
Da7-Tech/
mind

Persistent memory for AI coding agents: automatic capture, explainable recall, knowledge consolidation, privacy controls, and portable offline storage. One Python file, zero dependencies.

76
niuma996/
nium-wiki

AI coding tool skill (e.g., Claude Code) centered on Karpathy's LLM Wiki pattern turns codebases into wikis, auto-analyzes, and generates docs similar to DeepWiki and ZRead with diagrams.

37

Build AI agents that actually do things. Synapse is an open-source platform for creating, connecting, and orchestrating AI agents powered by any LLM — local, cloud or CLIs.

320

Your agent seeks what search can't find. A self-hosted perception MCP server that transcribes speech, reads behind logins, sees images and video frames, crosses languages, and remembers.

49
najmuzzaman-mohammad/
gawkbot

open source grok bot. gawk bots automate your menial work via AI models and build you microapps to manage the outcome, so that you have a false sense of control.

1.3k
aayoawoyemi/
Ori-Mnemos

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

323
raphasouthall/
neurostack

Local RAG layer and optimizer for your Markdown knowledge base. CLI + MCP server: grounded answers for any AI client, stale-note detection, session harvesting into memories. Local-first.

47

An always-on second brain you talk to. Voice notes in Telegram → typed, linked knowledge in your Obsidian vault. Runs 24/7 on the Claude subscription you already have.

366

Compile, verify, and run multi-agent DAGs across Pi, Codex, Claude Code, OpenCode, and Grok—with resume, replay, and incremental recomputation.

71
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
fabio-rovai/
open-ontologies

AI-native ontology engine: a Rust MCP server with tools for building, validating, querying, and reasoning over RDF/OWL ontologies. In-memory Oxigraph triple store, native OWL2-DL tableaux reasoner, SHACL validation, SPARQL, versioning. Single binary, no JVM.

492
alibaizhanov/
mengram

Human-like memory for AI agents — semantic, episodic & procedural. Experience-driven procedures that learn from failures. Free API, Python & JS SDKs, LangChain, CrewAI & OpenClaw integrations.

194
eli-labz/
Cognitive-Core-Skills

A universal, industry-neutral taxonomy of cognitive core skills (perception, memory, reasoning, planning, action, verification, learning, governance) for LLMs, SLMs, AI agents, and world models — with schemas, 159 skill cards, benchmarks, and CI.

165
RyjoxTechnologies/
Octopoda-OS

The open-source memory and observability layer for AI agents — persistent memory, loop detection, hash-chained audit trails, and a live dashboard, automatic on pip install.

490
juyterman1000/
entroly

Cut AI context cost without trusting the compressor. Every reduction is reversible, byte-exact recoverable, and carries an auditable receipt. Local-first, works through proxy, MCP, SDK, or agent wrapper.

443

Synthadoc: An open-source LLM knowledge compilation engine that turns raw documents into structured, local-first wikis. A transparent, human-readable alternative to traditional RAG, which can be self-managed and self-improved without the use of any tools.

1.2k
Orkas-AI/
Orkas-VideoStudio

Turn your coding agent into a video studio: describe a video in plain language, and your agent writes the timeline and produces the file.

486
maioio/
genesis-architect

Research-first architecture engine for Python, TS, Go and Rust. Mines GitHub Issues for real production failures before scaffolding, then audits drift, cycles and fragility in code you already have. Zero import cycles, zero critical anti-patterns - measured against itself.

49
vouchdev/
vouch
vouchdev/vouchConnectors

A git-native, review-gated knowledge base for AI agents: they propose writes, you approve them. Every claim cites a source, every change is a diff in your repo. MCP + CLI.

92
SamurAIGPT/
llm-wiki-agent

A personal knowledge base that builds and maintains itself. Drop in sources — Claude (or Codex/Gemini) reads them, extracts knowledge, and maintains a persistent interlinked wiki. Works with Claude Code, Codex, OpenCode, Gemini CLI. No API key needed.

3.5k

Agent Ops for your second brain - a 3D IDE for Obsidian built on Three.js. Visualize your vault as a code city, dispatch AI coding agents (Claude Code, Codex, Antigravity), post research quests, and watch your agent fleet work in real time.

93
AbubakrChan/
product-launch-motion

Claude Code skill for product launch motion design — make launch videos, promos and demo reels from code. HTML/CSS/GSAP compositions, word-locked voiceover sync, real camera moves, film grade, broadcast-loudness mastering. A director's discipline, not a template.

56
okf-memory/
okf-agent-memory

Git-native persistent memory for AI coding agents. Implements Google OKF v0.2 with sub-300µs in-memory BM25 search, embedded MCP server, and progressive disclosure. Slashes token bloat by 80% with zero external databases or dependencies. Built in pure Go.

547

Harness engineering applied to knowledge production: a self-evolving multi-agent newsroom that turns your documents into a cross-linked markdown wiki. A "reground" loop pulls published pages back in before they go stale — writer ≠ reviewer, local-first, a structured alternative to RAG.

85