Awesome AI AgentsAI Developer Toolkit

m0n0x41d/quint-code

⭐ 1391 Go repository created 2025-12-10

Haft, formerly named quint-code, is a Go command line tool that brings a versioned copy of the FPF source by Anatoly Levenchuk into the working context of an AI coding agent and maintains a local project graph for work that later sessions must rely on. The stated split is that a small reversible exchange can stay in conversation, while a decision that authorises work, a handoff another session must replay, or a claim needing fresh evidence becomes a typed project record. Rather than replacing FPF with a second pattern catalogue, Haft ships the pinned source, project-local application surfaces and durable records. The README carries explicit runtime truth labels that separate contract inclusion, exact-candidate evidence, published-product status and release authority, and it marks dense or hybrid retrieval as deferred research, stating that no claim of retrieval superiority over a pinned FPF file, ripgrep or built-in RAG is made before a separate benchmark. Installation is a shell script, after which haft init wires the tool into an agent host. Bare init opens an interactive multi-select on a terminal and fails rather than guessing in scripts or CI, so automation must name a host explicitly. Flags cover a core-only project ledger with no host carriers, Claude Code and Codex as the stable hosts, and experimental or legacy adapters for Grok, Pi, Hermes, Zed, Antigravity, Cursor, Gemini CLI and OpenCode, plus a repo-local skills variant and an MCP-only compatibility modifier. Per host it writes an MCP configuration, transformed skills into a global or repo-local directory, and a managed section delimited by markers inside CLAUDE.md or AGENTS.md, leaving content outside those markers untouched and failing before overwriting a foreign file. A separate project migrate command performs an additive database upgrade without touching host configuration.

https://github.com/m0n0x41d/quint-code

agent-memorymcpclicoding-agentsknowledge-management

Also in AI Developer Toolkit

Leonxlnx/taste-skill

Taste Skill provides portable AI Agent Skills designed to enhance the quality of AI-generated frontends and image-based design references, aiming to eliminate generic UI outputs.

unslothai/unsloth

Unsloth is a toolkit for fine-tuning and reinforcement learning of large language models, enabling faster training with significantly reduced VRAM usage across various advanced models and tasks.

reworkd/AgentGPT

AgentGPT is an open-source platform that allows users to assemble, configure, and deploy autonomous AI agents in a web browser to pursue custom goals by generating and executing tasks independently.

Gitlawb/openclaude

OpenClaude is an open-source command-line interface (CLI) coding-agent that supports various cloud and local model providers for unified AI-driven development workflows.

virgiliojr94/book-to-skill

A command-line tool that converts technical books, document folders or globs into structured agent skills in the open SKILL.md format, so coding agents load only the chapter relevant to a question.

google/adk-python

An open-source Python toolkit by Google for building, evaluating, and deploying sophisticated AI agents with flexibility, modularity, and integration within the Google ecosystem.

can1357/oh-my-pi

Oh My Pi is an AI coding agent for the terminal featuring hash-anchored edits, an optimized tool harness, LSP integration, and support for Python, browsers, and subagents.

millionco/react-doctor

React Doctor is an intelligent agent designed to diagnose and fix issues within React codebases, leveraging AI to improve code quality and developer efficiency.