Sandbox
661 repos for llm · Any agentClear
dcramer/
dex

Task tracking for Agents

382
artokun/
comfyui-mcp

Local-first, agent-native control plane for ComfyUI — MCP server + sidebar agent that generates images, video & audio, authors and runs workflows, and edits your live graph in natural language on ANY LLM (Claude, ChatGPT, Gemini, offline Ollama, or any hosted model). 178 tools, 36 AI skills, 55 installer packs. Local, LAN, VPS, or Comfy Cloud.

737

The fastest local AI engine for Apple Silicon. 4.2x faster than Ollama, 0.08s cached TTFT, 100% tool calling. 17 tool parsers, prompt cache, reasoning separation, cloud routing. Drop-in OpenAI replacement. Works with Claude Code, Cursor, Aider.

3.7k
icip-cas/
PPTAgent
icip-cas/PPTAgentFrameworks & SDKs

An Agentic Framework for Reflective PowerPoint Generation

5k
blurrah/
mcp-graphql

Model Context Protocol server for GraphQL

407
GopherSecurity/
gopher-mcp
GopherSecurity/gopher-mcpFrameworks & SDKs

C++ MCP SDK - build Model Context Protocol (MCP) servers and clients in C++ / CPP. Enterprise-grade security, observability, connectivity. Stdio, HTTP+SSE, Streamable HTTP, WebSocket, TCP transports. Bindings for Python, TypeScript, Go, Rust, Java, C#.

147
rome-os/
rome
rome-os/romeFrameworks & SDKs

Rome is the agentic OS.

488
AbyssCN/
oh-my-dag

The orchestration layer under your coding agent. Turns work into a typed graph, runs one model per node, and takes the verdict from outside the model — exit codes, write-set checks, and a cross-family verifier. MCP server, 50 tools, bring your own models.

39
IlyaGusev/
academia_mcp

Academia MCP server: Tools for automatic scientific research

91
Billy1900/
Midas
Billy1900/MidasFrameworks & SDKs

Compound Engineering Framework for Alpha Feature Research in Quant Finance

61

A Nostr MCP server that allows to interact with Nostr, enabling posting notes, and more.

38
PrefectHQ/fastmcpFrameworks & SDKs

🚀 The fast, Pythonic way to build MCP servers and clients.

28k
wanshuiyin/
Anti-Autoresearch

Don't trust an autoresearch paper at face value. Reviewer-side integrity forensics (self-consistency + fabrication), deterministic verdict. 61 signals: 46 integrity hack-patterns (families A–H, verdict-bearing) + 13 zero-weight AI writing-style impressions (AIS) + 2 advisory. Not an opaque AI-text classifier. The dual of ARIS.

152