by mahmoudsajjadi
A curated catalog of verified AI coding assistants, autonomous agents, open‑weight foundation models, and Model Context Protocol (MCP) servers, complete with benchmarks, decision guides, and practical documentation to help developers pick the right tool for any workflow.
Awesome AI Coding Tools aggregates and maintains a searchable list of AI‑driven coding assistants, agentic IDEs, CLI pair programmers, parallel‑agent platforms, MCP servers, open‑weight models, local execution engines, automated testing utilities, and autonomous software‑engineering agents. Each entry is verified, includes a brief neutral description, a link, and key licensing or pricing information. The repository also provides visual decision guides, a tool‑decision matrix, hardware sizing guides, benchmark results, and extensive documentation for deeper dives.
README.md and navigate to the desired section (e.g., Standalone Agentic IDEs, Terminal & CLI Pair Programmers, MCP Servers).| Scenario | Recommended catalog sections |
|---|---|
| Beginner developer wants in‑editor autocomplete and chat without any terminal setup | 1‑Click Editor Extensions (Codeium, Continue.dev) |
| Intermediate engineer prefers private, offline models and terminal‑centric workflows | Terminal & CLI Pair Programmers (Aider, Claude Code) + Local Execution Engines (Ollama, vLLM) |
| Team building autonomous CI bots that open PRs and run tests | Autonomous Software Engineers (OpenHands, SWE‑agent) + Running Agents in Parallel (AgentsMesh, Codama) |
| Researcher evaluating coding LLMs on SWE‑bench | Top Open‑Weight Coding Models (Codestral, DeepSeek‑Coder‑V2) + Benchmarks doc |
| Organization needing a secure, self‑hosted MCP server for browser or git interactions | Model Context Protocol (MCP) Servers (BrowserTools MCP, GitHub MCP Server, codebase‑memory‑mcp) |
Q: How often is the catalog updated? A: The repository is actively maintained; new tools are added via Pull Requests and CI validates the markdown structure.
Q: Are the listed tools free? A: Each entry lists its licensing and pricing model. Many have free tiers or open‑source licenses; others are commercial with paid plans.
Q: Can I run the entire stack offline? A: Yes. Combine Local Execution Engines (Ollama, llama.cpp) with open‑weight models (Qwen2.5‑Coder, Codestral) and CLI agents (Aider, Claude Code) for a 100 % offline workflow.
Q: How do I contribute a new tool? A: Fork the repository, add a markdown entry under the appropriate section with a valid URL and neutral description, run the CI locally, and submit a PR.
Q: Where can I find benchmark results for autonomous agents? A: See the Benchmarks & Architecture document (docs/BENCHMARKS.md) which contains SWE‑bench leaderboard tables and evaluation methodology.
A curated catalog of verified AI coding assistants, autonomous software engineering agents, open-weight foundation models, and Model Context Protocol (MCP) servers. Maintained by Mahmoud Sajjadi.
Use these questions to narrow down the right tool for your setup:
Where do you want to code?
Do you require 100% offline privacy and zero API fees?
Need a side-by-side trade-off analysis across archetypes (IDE vs CLI vs Async vs Local)?
Curious about real-world daily developer workflows?
Do you need multi-agent orchestration or parallel sessions?
Do you want automated PR reviews or regression testing in CI?
Are you researching autonomous software agents?
/evidence, enforces deterministic hollow-answer checks, and exports manual verification checklists with multi-model and MCP client support.npx -y ironheights mcp) that lets Claude Code, Cursor or Codex check an agent skill or MCP config before installing it, returning an A–F grade with findings for prompt injection, credential reads and remote-exec installs. Rule-based and pre-1.0, so it misses many plain-language attacks. Apache-2.0.[[wikilinks]] in a single SQLite file; embeddings run locally via ONNX. MIT.ollama run qwen2.5-coder).See docs/CHANGELOG.md for recently added and removed tools, schema updates, and catalog revision history.
Contributions are welcome! Please read CONTRIBUTING.md for guidelines on suggesting or adding tools. Every entry must have a valid URL, neutral factual description, and clear license/pricing terms.
Please log in to share your review and rating for this MCP.
Explore related MCPs that share similar capabilities and solve comparable challenges
by headroomlabs-ai
Compress tool outputs, logs, files, RAG chunks, and conversation history before they reach the LLM, keeping answers identical while saving up to 95% of tokens for JSON payloads.
by modelcontextprotocol
A Model Context Protocol server for Git repository interaction and automation.
by zed-industries
A high‑performance, multiplayer code editor designed for speed and collaboration.
by modelcontextprotocol
Model Context Protocol Servers
by modelcontextprotocol
A Model Context Protocol server that provides time and timezone conversion capabilities.
by cline
An autonomous coding assistant that can create and edit files, execute terminal commands, and interact with a browser directly from your IDE, operating step‑by‑step with explicit user permission.
by upstash
Provides up-to-date, version‑specific library documentation and code examples directly inside LLM prompts, eliminating outdated information and hallucinated APIs.
by daytonaio
Provides a secure, elastic infrastructure that creates isolated sandboxes for running AI‑generated code with sub‑90 ms startup, unlimited persistence, and OCI/Docker compatibility.
by continuedev
Enables faster shipping of code by integrating continuous AI agents across IDEs, terminals, and CI pipelines, offering chat, edit, autocomplete, and customizable agent workflows.