Fission-AI/OpenSpec
Spec-driven development (SDD) framework and CLI tool for AI coding assistants, providing structured workflows for proposing, implementing, and archiving code changes. MIT licensed.
fern-api/fern
Open-source SDK generator for REST APIs. Generate type-safe API clients in TypeScript, Python, Go, Java, and more from OpenAPI specs. Powers SDKs for companies like OpenAI, Anthropic, and Cloudflare. Apache 2.0 licensed.
github/spec-kit
Toolkit and CLI for Spec-Driven Development that integrates with AI coding agents to generate structured code implementations from executable specifications. MIT licensed.
archcore-ai/archcore
Git-native context engineering and spec-driven development for AI coding agents. Apache 2.0 licensed.
JoaquinRuiz/SpecJudge
CLI that reads a project's specification files and recommends which LLM fits the work, using a local judge model via Ollama and citing the spec fragment behind each demand level. MIT licensed.
JetBrains/thinkrail
Agentic IDE built around pi with Git-worktree isolation, durable SPEC.md project knowledge, concurrent agent sessions, MCP servers, and desktop or CLI hosts. Apache-2.0 licensed.
addyosmani/agent-skills
Production-grade engineering skills and quality gates for AI coding agents, packaging developer workflows like spec refinement, planning, and testing.
openai/symphony
Turns project work into isolated, autonomous implementation runs. Monitors work boards, spawns agents to handle tasks, and provides proof of work including CI status, PR reviews, and walkthrough videos. Engineering preview for managing work instead of supervising coding agents. Apache 2.0 licensed.
miurla/morphic
AI-powered search engine with a generative UI. Supports multiple AI providers (OpenAI, Anthropic, Google, Ollama) and search providers (Tavily, SearXNG, Brave). Features smart search modes, widgets, and image/video search. Apache 2.0 licensed.
cortex-docs/cortex
Generates typed SDKs, API documentation, and MCP servers from OpenAPI, AsyncAPI, GraphQL, Protocol Buffer, OpenRPC, and Markdown sources. MIT licensed.
google-labs-code/design.md
A format specification for describing visual identity to coding agents, combining YAML tokens and markdown prose to give agents a structured understanding of design systems. Apache 2.0 licensed.
AlexsJones/llmfit
Terminal tool and TUI that right-sizes LLM models to hardware specs and scores local compatibility across GPU, CPU, and RAM. MIT licensed.
virgiliojr94/book-to-skill
CLI tool that distills technical books, documents, and reference materials into structured, on-demand agent skills. MIT licensed.
159753a52/llm-vram-calculator
Dependency-free TypeScript core that estimates inference memory (weights, KV cache, overhead) of any Hugging Face model from its config.json and safetensors metadata, covering MoE, MLA, sliding-window and linear-attention layers; runs in the browser at [modelvram.com](https://modelvram.com/llm-vram-calculator/). MIT licensed.
milanglacier/minuet-ai.nvim
Neovim plugin offering code completion as-you-type from popular LLMs including OpenAI, Gemini, Claude, Ollama, Llama.cpp, Codestral, and more. GPL-3.0 licensed.
anthropics/knowledge-work-plugins
Collection of role-specific plugins and sub-agents for Claude Cowork and Claude Code. Apache 2.0 licensed.
google-labs-code/stitch-skills
A library of agent skills and plugins designed to work with the Stitch MCP server, following the Agent Skills open standard. Apache 2.0 licensed.
CopilotKit/CopilotKit
Best-in-class SDK for building full-stack agentic applications, Generative UI, and chat applications. Creators of the AG-UI Protocol adopted by Google, LangChain, AWS, and Microsoft. MIT licensed.
vercel-labs/json-render
Generative UI framework for rendering dynamic, type-safe interfaces from structured JSON streamed by LLMs and agents. Apache 2.0 licensed.
landedjobs/ai-engineer-portfolio-projects
85 buildable AI engineering project briefs grouped by theme (RAG, agents, evals, fine-tuning, multimodal), each with difficulty, skills shown, and reference resources. MIT licensed.
Michael-A-Kuykendall/shimmy
Python-free Rust inference server with OpenAI API compatibility. Supports GGUF and SafeTensors formats with hot model swap, auto-discovery, and single binary deployment for zero-dependency inference. Apache 2.0 licensed.
apache/ossie
Vendor-neutral specification to standardize semantic models across analytics, BI, and AI agent platforms. Apache 2.0 licensed.
agentlas-ai/Agentlas-OS
Local-first, model-agnostic environment for building, borrowing, and orchestrating specialist agents and teams across supported LLM hosts, with owner-scoped packages and host-enforced permissions. Apache 2.0 licensed.
langfuse/langfuse
#1 open-source LLM observability platform.