Coding Agent Python Packages

cuga

CUGA is an open-source generalist agent harness for the enterprise, supporting complex task execution on web and APIs, OpenAPI/MCP integrations, composable architecture, reasoning modes, and policy-aware features.

pydantic-deep

Build Claude Code–style deep agents in Python: tool-calling, sandboxed execution, multi-agent teams, skills, checkpoints, and unlimited context — all on Pydantic AI.

drydock-cli

DryDock - Local CLI coding agent optimized for SWE-bench.

cocoindex-code

A super light-weight embedded code search engine CLI (AST based) that just works - saves 70% token and improves speed for coding agent 🌟 Star if you like it!

cafitac-hermit-agent

Quiet MCP executor for Claude Code and Codex. Offload edits, tests, refactors, and commits to cheaper local or flat-rate models.

google-agents-cli

The CLI and skills that turn any coding assistant into an expert at creating, evaluating, and deploying AI agents on Google Cloud.

neuralbrok

NeuralBroker — A VRAM-aware LLM router. Daemon polls GPU every 500ms, routes requests to local Ollama or cloud Groq based on real-time VRAM state. Single OpenAI-compatible endpoint at localhost:8000

hcom

Let AI agents message, watch, and spawn each other across terminals. Claude Code, Gemini CLI, Codex, OpenCode

omega-memory

Cross-model memory for AI agents. Local-first, works with Claude, GPT, Gemini, Cursor, Claw Code, and any MCP client

claude-status

Beautiful, informative status line for Claude Code. Zero dependencies, cross-platform. pip install claude-status

leashd

Safety-first agentic coding framework. Three-layer safety pipeline (sandbox, YAML policies, human-in-the-loop approval) for AI coding agents. Pluggable runtimes (Claude Code, Codex), autonomous task orchestrator, full audit trail.

swampo

The most complete skill pack for Claude Code — 42 curated skills for security, pentest, productivity & files + 23 slash commands

stashai

Shared memory for your team's coding agents

wbcli

Lightweight multi-agent orchestrator for iterative development

attocode

A series of lessons, 0 to hero ai coding agent building guide.

ntn

Minimal AI coding agent powered by Claude Opus 4.7 (adaptive thinking), GPT-5.5, or OpenRouter models (DeepSeek, Kimi, Hunyuan). Runs commands natively in your shell (PowerShell, bash, zsh).

sigit-code

A local coding agent powered by Onde Inference.

state-trace

Graph-native working memory for coding agents with causal retrieval and bounded capacity.

pilot-code

A harness for single and group of AI models and their replicas to perform a wide range of tasks, from coding and reasoning to more specialized operations.

kittycode

A minimal, hackable AI coding agent with a composable tool loop and modular skills

local-ai-agent-orchestrator

Multi-agent local LLM orchestrator for LM Studio: planner→coder→reviewer, SQLite queue, memory-safe model swaps. GPL-3.0 · CLI: lao

serenecode

Verification framework for AI-generated Python — test coverage, property testing, and symbolic execution

sutrakit

Sutracli is an AI-powered code manager for coding agents. It spawns agents for multiple projects, connects repos through cross-indexing, and builds dependency graphs for better change suggestions. By automating planning and updates, it helps teams reduce development cost, save time, and improve productivity.

aidocs-mcp

The orchestration layer for AI coding agents — persistent memory, conductor, dashboard, and multi-agent workflows. Works with Claude Code, Codex, OpenCode, Cursor. Apache 2.0.