Alternatives and similar repositories for model_spec

Users that are interested in model_spec are comparing it to the libraries listed below

• augmentcode / augment-swebench-agent
  The #1 open-source SWE-bench Verified implementation
  ☆853Updated 7 months ago
• modelcontextprotocol / mcpb
  Desktop Extensions: One-click local MCP server installation in desktop apps
  ☆1,689Updated this week
• modelcontextprotocol / docs
  Documentation for the Model Context Protocol (MCP)
  ☆424Updated 10 months ago
• openresponses / openresponses
  ☆757Updated this week
• openai / codex-universal
  Base docker image used in Codex environments
  ☆781Updated 2 weeks ago
• safety-research / bloom
  bloom - evaluate any behavior immediately  🌸🌱
  ☆1,152Updated 3 weeks ago
• openai / build-hours
  Build hours code to share.
  ☆686Updated 2 weeks ago
• microsoft / debug-gym
  A Text-Based Environment for Interactive Debugging
  ☆293Updated this week
• safety-research / petri
  An alignment auditing agent capable of quickly exploring alignment hypothesis
  ☆874Updated this week
• anthropics / claude-agent-sdk-demos
  Claude Code SDK Demos
  ☆1,372Updated last month
• SWE-agent / SWE-ReX
  Sandboxed code execution for AI agents, locally or on the cloud. Massively parallel, easy to extend. Powering SWE-agent and more.
  ☆424Updated last week
• huggingface / skills
  ☆1,151Updated last week
• cline / mcp-marketplace
  This is the official repository for submitting MCP servers to be included in Cline's MCP Marketplace. If you’ve built an MCP server and w…
  ☆753Updated 7 months ago
• OpenHands / open-operator
  Open-source resources on agents for computer use.
  ☆398Updated 4 months ago
• modelcontextprotocol / create-python-server
  Create a Python MCP server
  ☆476Updated last year
• langchain-ai / langgraph-cua-py
  An implementation of a computer use agent (CUA) using LangGraph
  ☆198Updated 10 months ago
• anthropic-experimental / agentic-misalignment
  ☆562Updated 7 months ago
• TheAgentCompany / TheAgentCompany
  An agent benchmark with tasks in a simulated software company.
  ☆635Updated 2 months ago
• microsoft / TypeAgent
  Sample code that explores an architecture for using language models to build a personal agent that can work with application agents.
  ☆608Updated this week
• togethercomputer / open_deep_research
  Together Open Deep Research
  ☆358Updated 9 months ago
• harishsg993010 / LLM-Research-Scripts
  ☆434Updated last year
• MoonshotAI / K2-Vendor-Verifier
  Verify Precision of all Kimi K2 API Vendor
  ☆507Updated last week
• langchain-ai / mcpdoc
  Expose llms-txt to IDEs for development
  ☆922Updated 6 months ago
• michaellatman / mcp-get
  ☆505Updated 2 months ago
• eliasjudin / oai-skills
  The contents of /home/oai/skills in ChatGPT's code interpreter environment
  ☆509Updated last month
• willccbb / claude-deep-research
  Claude Deep Research config for Claude Code.
  ☆225Updated 10 months ago
• OpenHands / software-agent-sdk
  A clean, modular SDK for building AI agents with OpenHands V1.
  ☆476Updated this week
• marckrenn / claude-code-changelog
  ☆521Updated last week
• ghuntley / claude-code-source-code-deobfuscation
  This is a cleanroom deobfuscation of the official Claude Code npm package.
  ☆818Updated 11 months ago
• openai / completions-responses-migration-pack
  Developer toolkit to migrate applications from the legacy OpenAI Completions/Chat Completions APIs to the unified Responses API, guided b…
  ☆98Updated 5 months ago