Code agents

Pydantic AI providers and model factory for OpenCode Zen and OpenCode Go.

Enabling Next-Gen LLM Applications via Multi-Agent Conversation Framework

Utility for examining python source files to ensure proper documentation. Lists missing docstrings, and calculates overall docstring coverage percentage rating

Core module containing code to run PyFarm's agent.

Add animations to revealjs presentations from Python code-blocks.

Python code fragments

Python wrapper for llama.cpp server - OpenAI API compatible backend with auto device detection

Leverage LLMs to generate and execute robust code dynamically through an intuitive and easy-to-use API!

A Python framework for building modular, extensible LLM applications through composable Elements in a flow-based architecture. Pyllments enables developers to create both graphical and API-based LLM applications by connecting specialized Elements through a flexible port system, with built-in support for UI components and LLM integrations.

large language model Programming - Type safe structured generation

Fast and lightweight multimodal LLM inference engine for mobile and edge devices

Lightweight bridge connecting coding agents to PyMOL via TCP socket

A tool for processing code repositories into semantic chunks for analysis with LLMs, especiallyNotebookLM.

A simple package to run a ReAct agent with Ollama and tools with privileges to run code inside a docker container.

Model-driven development of Python applications.

Generate manifest of public symbols win python projects w/docstrings

Catch silent agent failures in CI. Behavior lint for LLM agents, powered by agent-failure-debugger.

Use Claude Code in your pytests, or pytest your own Claude Code agents — or both

input() for Claude Code agents

Easy to use and powerful AI Agent development framework.

Python hooks for Claude Code

Auto generate code using openapi.

AI-powered code quality analysis tool using Groq Llama

Six MCP servers for the full QA STLC — test cases, Gherkin BDD, self-healing Playwright code, Helix-QA file writing, Jira Cloud integration, and one-shot migration of existing Playwright projects into the Helix-QA layout. Both ADO and Jira pipelines run: fetch → test cases → Gherkin → Playwright → Helix-QA. Ships an 8-strategy LocatorHealer with a live HealingDashboard that writes confirmed selectors back to source. MSAL OAuth for ADO, OAuth 2.0 (3LO) for Jira Cloud.

Code coverage for QML

QuickAgents - AI Agent Enhancement Toolkit with Document Understanding, Self-Evolution and Unified UTF-8 Encoding

Qwen-Agent: Enhancing LLMs with Agent Workflows, RAG, Function Calling, and Code Interpreter.

Qwen + Claude Code Router bootstrapper

A powerful RAG system for querying code repositories using tree-sitter parsing, LanceDB vector storage, and Qwen models

A terminal-based agent for interacting with Qwen3-Coder models

Indexador de contexto enriquecido para optimización de RAG en LLMs con soporte Agentic Scaffolding, Auto-Sync, Trazabilidad, Persistencia tmux e Integración Claude Code

Real-time debugging SDK for RAG pipelines

Next.js 公式ドキュメント RAG CLI (next-devtools-mcp)

Agentic RAG SDK - MCP server for grounding AI coding agents with Voyage AI + Qdrant hybrid retrieval

Cross-encoder reranker utility for LangChain documents

Semantic code chunking for LLM processing with policy-based configuration

Interactive terminal debugger and optimizer for RAG chunking pipelines

CLI tool for interacting with Raga Canvas no-code agent deployment platform

Git for data scientists - manage your code and data together

Experimental Ragas Evaluation UI and Library

A package that can be used to create RAGs with a single line of code.

Building blocks for rapid development of GenAI applications

Building blocks for rapid development of GenAI applications

Building blocks for rapid development of GenAI applications

A CLI application for ragbits - building blocks for rapid development of GenAI applications

Building blocks for rapid development of GenAI applications

Building blocks for rapid development of GenAI applications

A library to build Retrieval-Augmented Generation applications with only a few lines of code.

Observability SDK for RAG pipelines — auto-trace every stage of your RAG app.

RAGDK - Retrieval Augmented Generation Develoment Kit

Retrieval-Augmented Generation Driven by Offline Local LLMs — a fully-local RAG system for JIRA tickets, code, and PDFs, powered by Ollama.

Intelligent CLI-based Project Context Engine with MCP server support

Fix ragged right edges in LLM-generated ASCII/Unicode box diagrams

RAGLens CLI for debugging retrieval behavior in RAG systems

RAGNARDoc (RAG Native Automatic Reingestion for Documents) is a tool that runs natively on a developer workstation and automatically ingests local documents into various Retrieval Augmented Generation indexes. It is designed as a companion app for workstation RAG applications which would benefit from maintaining an up-to-date view of documents hosted natively on a user's workstation.

Local semantic code recall with mxbai embeddings and SQLite

Develop highly-concurrent web scrapers, easily.

Local-first memory and RAG system for Claude Code - semantic search over code, docs, and team knowledge

Ragul — an agglutinative programming language

Ralph - Autonomous Claude Code Agent Runner

Library for fetching random user agents based on device type (desktop, mobile, etc.).

A Package for reranking with LLMs (pointwise, pairwise, and listwise)

A sample Python project

Claude Code CLI wrapper with tmux session management, subprocess execution, and OAuth token handling

Remote control for Claude Code via Telegram

Research & Development Agent

Microsoft's Bing Chat AI

Python library for executing Agent Flows - visual, no-code workflows for AI agents

Code-coverage visualizer for binary-matching game reverse engineering

Security Remediation Agent for Python codebases

A package aiming to using LLM to analyse relational data. Still in developing.

Open-source autonomous AI agent: label an issue, get a tested pull request. Runs in your CI (GitHub Actions, GitLab CI, Bitbucket Pipelines, or Azure Pipelines). Standalone: no inter-package dependencies.

Persistent knowledge memory and code dependency graph for AI agents - Rust, Postgres, pgvector, MCP

Manage headless remote Claude Code sessions via tmux + Tailscale

Agent daemon for Remote AI Maestro — manages PTY sessions and AI agent subprocesses on remote machines

Build local issue and pull request context for coding agents on GitHub and GitLab.

Search your code repository using GPT4.

CLI tool to convert a code repository into LLM-friendly markdown

A tool to gather project context into a single file for LLMs

A command-line tool to make a code repo digestible for an LLMs

An LLM-Powered Framework for Repository-level Code Documentation Generation.

SWE-bench for your codebase. Turn merged PRs into reproducible coding-agent benchmarks.

A terminal companion for Claude Code. While Claude thinks for 23 seconds, reSkill hands you a quiz about the exact code it's working on.

Rev - Autonomous AI Development System with Multi-Agent Orchestration

Collaborative AI code review MCP server -- shared whiteboard for multi-agent code review via MCP

Chrome DevTools for AI agents — record, inspect, fork, replay, diff.

Cross-agent installer for Robot Framework agent skills (Claude Code, Copilot, Codex, Cursor, Goose, OpenCode, Claude Desktop)

A terminal chatbot, powered by Groq Cloud API (Windows / macOS / Linux)

A plug-in to measure code coverage in RiveScript with python

A quality-assurance engine for LLM-generated code

A python package developed to play `Road Rage` game from hand gestures.

Let language models run code.

🤗 rosagents: a barebones library for uas and robotics agents. Agents write python code to call tools or orchestrate other agents.

AI agent toolkit for Rossum: document workflows conversationally, debug pipelines automatically, and enable agentic configuration of intelligent document processing.

Local-first AI coding assistant powered by Ollama, OpenAI, or Anthropic

A fast, modular, secure, and auditable toolkit to integrate with Azure OpenAI — with a friendly CLI and dev-first architecture.

Fast Python bindings for Project Haystack — types, codecs (Zinc/Trio/JSON), filters, ontology, and Xeto support powered by Rust

An AI coding agent you can actually trust - with built-in impact preview

MCP server exposing the SaferAgenticAI safety framework (canonical criteria + Implementation Patterns layer) to coding assistants.