v1.95.0 · MIT
Spec-driven development framework — AI agents that think before they type
v1.0.11 · MIT
Verified npm launcher for the open-source ContextStream Rust MCP server
v0.8.0 · Apache-2.0
🐳 DeepSeek Harness Desktop
v0.8.3 · MIT
Team memory for engineers and their AI agents. Lives in your repo. Shared through Git.
v1.16.0 · MIT
Make any repo AI-first - write sustainable code from the start, or refactor a legacy codebase to prepare it for agent-driven development.Building blocks for Claude Code: subagents, slash commands, hooks, and workflow patterns. Copy what you need. A working developer's stack for Claude Code.
v1.1.0 · MIT
Compare multiple skills on the same task and pick the winner.
v4.0.0 · Apache-2.0
A 267-skill research graph in pure markdown — 51 research operations built from 216 single-purpose steps, composed in any order with explicit backtracking. One npx install, no runtime, no MCP bindings. The AI is the researcher; you set the direction.
v3.6.1 · MIT
Greptile code review from your terminal
v0.7.12 · Elastic-2.0
Shared team knowledge, leaked-secret alerts, ranked code findings and tracked tasks, across every AI coding tool you use
v1.5.0 · MIT
Notes for you, Memory for your agents. / 内置 Deepseek harness Agent / 适用 办公 & 写作 & Coding
v3.46.0 · Apache-2.0
Security infrastructure your AI can't be — deterministic, current past your model's training cutoff, whole-repo-aware, author-independent. Security MCP for vibe coding. 530 rules, 39 tools, CLI + doctor. Prompt-level shift-left security (secure_prompt — e
v1.0.1 · MIT
Evidence-first reading for AI agents — turn articles, books and PDFs into traceable claims, evidence, source locations and knowledge maps.
— · MIT
Skills & plugins for agentic commerce : UCP, ACP, AP2, A2A, WebMCP, Magento 2, BigCommerce, WooCommerce
v0.3.18 · Apache-2.0
:star: AI-assisted development workflow that produces understanding alongside code. Teach, capture decisions, document, assemble reviews.
v1.0.169 · no license
Context window optimization for AI coding agents. Sandboxes tool output (98% reduction), persists session memory, and enforces routing across 17 platforms via MCP + hooks.
v0.1.0 · MIT
Multi-agent codebase review for PRs, CI, and downstream fork syncs.
v0.3.0 · MIT
Documentation memory for AI coding agents—route project knowledge, reduce repeated context loading, and validate living Markdown docs.
v0.32.3 · MIT
Local history ingestion, storage, evidence, SDK, CLI and MCP server.
— · no license
Opinionated AI agent skills for building applications with MotherDuck
v6.12.19 · MIT
Use your Claude and ChatGPT subscriptions in Cursor, Cline, Aider, Claude Code and the Agent SDK — at subscription pricing, not per-token API bills. One local Anthropic + OpenAI-compatible endpoint: either plan answers either wire shape, with automatic fa
v0.56.1 · MIT
Autonomous PR CI monitor and review-comment resolver for agentic coding tools
v0.3.0 · MIT
Show the instruction graph your coding agents actually receive.
— · MIT
The world's first open-source AI-native vector design tool and the first to feature concurrent Agent Teams. Design-as-Code. Turn prompts into UI directly on the live canvas. A modern alternative to Pencil.
v1.12.0 · Apache-2.0
Your coding agent designs terrible UI. stitch-kit wires it into Google Stitch MCP and teaches it the whole pipeline — ideation, screen generation, design systems, production components.