Code agents

ASTrea - Autonomous Software Engineering Agent

Athena — a local-first agentic PKM that helps you make better decisions with your own context. Persistent memory, structured reasoning, and governed AI agents that work across any LLM.

Code to load data from AWS S3 cloud storage

Code to load data from Azure Blob cloud storage

Code to load data from Google Cloud Storage

Estimate performance, energy, cost, and break-even tradeoffs for pruning coding LLM deployments.

Python code coverage automation

Headless Agent Studio Open protocol, trace-store, sidecar, and export CLI.

An open-source offline AI agent debugging tool: record, replay, analyze failures, and track API costs—free and local.

Official Python SDK for AgentNet -- AI engineering work as a service.

Auto LLM Chatbot is a Python package that simplifies chatbot development by automatically managing chat history using local vector databases like Chroma DB.

Evidence-driven autonomous reverse-engineering agent with agentic Ghidra analysis, independent LLM verification, candidate validation, and parity checks

Hierarchical multi-cluster coding swarm CLI

Python SDK for AutoCoder RAG - 便于在Python代码中调用auto-coder.rag run功能

A programming framework for agentic AI

AutoGen tools for the Ejentum Reasoning Harness. Eight agent-callable async functions returned by ejentum_tools(api_key=...): four dynamic (reasoning, code, anti_deception, memory) and four adaptive (adaptive_reasoning, adaptive_code, adaptive_anti_deception, adaptive_memory) that pre-fit the operation to the task via an adapter LLM. Each call retrieves a structured cognitive injection: a natural-language procedure plus an executable reasoning topology.

An AutoGen extension that allows code execution using YepCode's secure serverless runtime

AWS Fargate code executor for AutoGen - Run code securely and scale beyond local resources

MPC server provides code interpreter with kubernetes workload

A simple Python library

Import wisdom, export code.

Build apps autonomously with Claude Code CLI

Open source terminal-based AI coding agent built from scratch

Some debugging tools for AV engineers to use

A sample Averaging project

Find CloudFormation stacks across AWS accounts using SSO

Pydantic v2 models for AWS devops_agent, shipped as a PEP 420 namespace extension of aws-resource-validator.

Claude Code adapter for axor-core governance kernel

AzForge Agent for secure, compliant resource deployment

A markdown-first programming model for building AI agents on Azure Functions, powered by the Microsoft Agent Framework.

Interface between LLMs and your data

A pre-commit security scanner that detects prompt injection vulnerabilities in LLM application codebases through static analysis

A developer-friendly helper for OpenAI's Batch API

A tool to generate python code with AWS bedrock abstraction.

Library for Bedrock based GenAI Utility for AWS Based development

AWS Bedrock and Claude Platform on AWS API keys security toolkit: offline decoder, phantom user discovery, incident response, cleanup, preventive SCPs and detection content.

Minecraft Bedrock Packets Codec Library

Minecraft Bedrock Packets Codec Library

BeeOS DeviceAgent — AI-powered device control agent with ACP, MQTT, and WebRTC

Advanced AI Shell Command Assistant

Large Language Model Develop Toolkit

Set up Claude Code for any project in one command

CLI for orchestrating structured debates between AI agents

IPython magic command to format python code in cell using black.

Headless agent daemon exposing local agent CLIs (Claude Code, Codex) over a Unix socket.

AI coding agent with ReAct pattern and tool calling.

Local API to collect and compute data on used device and running applications to give insight on their environmental impacts.

Bog Agents CLI — your coding agent in the terminal, patient as still water. 80+ slash commands, any LLM provider (Anthropic, OpenAI, Bedrock, Google, Ollama and more), persistent memory, plan mode, /qa acceptance-criteria harness, /peat personal scheduler, /record + /replay, in-memory secrets vault, MCP marketplace with 35+ servers, deep doctor, panic dumps, and a matte swamp/neon-green TUI. One install, no code required. Pass through in harmony.

Run Claude Code locally on the Bonsai 8B 1-bit MLX model.

Open Source Multi-Agent AI Dev Team

Improve development of retrieval augmented generation (RAG) applications at the BR AI + Automation Lab.

breadth first fragmentation package

基于 Agent 的服务自动化修复系统

Claude-powered git pre-push diff reviewer for indie OSS projects.

A template for nbdev-based project

byLLM Provides Easy to use APIs for different LLM Providers to be used with Jaseci's Jaclang Programming Language.

BYOM AI Agents - A terminal-based AI coding agent that works with any LLM provider (OpenAI, Anthropic, Google, etc.)

This is a reserved placeholder package to mitigate dependency confusion risks.

This is a reserved placeholder package to mitigate dependency confusion risks.

A multi-provider Python code execution and dependency management agent

cLLM is an Open-source library that use llama-cpp-python and llama.cpp and provide a Low and High level API and allow developer to be more pythonic.

Openmp C pragma Modifier in Source Code

cachly.dev adapters for LangChain, AutoGen & CrewAI – persistent memory, semantic long-term memory, and semantic cache for AI agents

Cost-optimized MCP coding executor for Claude Code and Codex.

Persistent memory for LLM coding agents — local-first, model-agnostic, SQLite-backed

Turn a team meeting into shipped code. Recording in, working tested PR out, humans approving at every gate.

On-premise, sandboxed AI agent platform for regulated sectors.

CaveAgent is a tool-augmented agent framework that enables function-calling through LLM code generation and provides runtime state management. Unlike traditional JSON-schema approaches, it natively handles complex Python objects like DataFrames and ndarrays within a persistent runtime, enabling lossless data flow across multi-turn interactions.

The code is a Python package for managing file storage on either AWS S3 or a local machine. It provides methods for listing, searching, and storing files. The package includes two classes, Aws and Local, which implement the same set of methods for accessing and manipulating files in S3 and a local directory.

Manage and launch Claude Code projects from your terminal

Context-aware Code Evolution Agent - AI-powered code analysis and transformation

AI coding assistant with structured CDD workflows - LLM agnostic terminal agent

AI-first development framework for Claude Code - conversational specs, autonomous planning, context-aware implementation

Constructs for Dev::FSx::StorageVirtualMachine

Code to perform analysis on segmentations like those produced by CellMap

A local agent for code development using Cerebras API

Ready-to-use hooks for Claude Code: bash validation, git reminders, file limits, context injection, and session checkpoints.

Template agent definitions for Claude Code: coordinator, architect, quality-gate, and worker roles with team composition files.

AST-based code analysis toolkit: symbol extraction, dependency graphs, semantic search, impact analysis, and repository mapping.

SQLite event database for AI agent session tracking and analytics

A verification language for AI agent protocols — session types, compiler, code generation, and formal verification

Quality gates for AI agent swarms: content scoring, hook validation, and agent sync

Git-native, human-readable session memory for AI agents. Every decision is a commit, every state is Markdown.

Debug Python code with ChatGPT3 and get error explanations and corrected code.

Pre-commit hooks collection that utilizes ChatGPT and OpenAI platform to validate modifications made to the codebase.

A command line tool for interacting with ChatGPT to help with development

A wrapper package which takes care of API call robustness to ensure developers quickly and easily develop CHatGPT based applications.

A visual node-based programming system for creating and managing agent-based workflows.

AI-powered developer onboarding and context recovery system for git repositories

AI chat assistant in your terminal powered by OpenAI ChatGPT models.

Chio-governed tool wrappers for coding agents -- safe file, shell, and git access with a zero-config default policy

CLI tool for AI agents to observe and interact with Chrome via CDP

Google Gemini API plugin for the cjm-transcription-plugin-system library - provides speech-to-text transcription with configurable model selection and parameter control.

Mistral Voxtral plugin for the cjm-transcription-plugin-system library - provides local speech-to-text transcription through vLLM with configurable model selection and parameter control.

A CKAD (Certified Kubernetes Application Developer) exam preparation assistant

27 practical AI tools (MCP server + CLI) — structured frameworks, data processing, and real computation for writing, analysis, coding, and business tasks.

Control Claude Code remotely via Slack — approve permissions, answer questions, and continue sessions while AFK

Audit your Claude Code agent architecture. Detect autonomy risks, observability gaps, and rule coverage issues.

Multi-session Claude Code dispatch from Telegram

Activation-gap diagnostic for Claude Code — compares what's configured on disk against what actually fires in sessions, across five capability axes.