Agentic Coding Python Packages

tdd-guard-pytest

Automated TDD enforcement for Claude Code

spruce-grove

gran-lund, sv: spruce grove - an agentic coding CLI grown in the grove. Inspired by Code Puppy. Together we are better. Always.

the-loopy-one

The loop for everything!

spec-kitty-cli

Spec-Driven Development with organizational governance. Specs tell AI agents what to build; Charter governs how they build it. Git-native missions, enforceable workflows, and consistent engineering standards across AI coding agents and harnesses.

agentstreamdeck

Mission control for AI coding agents on your Stream Deck Mini. Monitor six sessions with live status indicators and one-touch window switching. Includes adapters for OpenCode, Claude Code, GitHub Copilot, Gemini CLI, and Cursor CLI.

vaultspec-core

Decision-driven harness for coding agents, and humans.

agentbundle

The complete AI operating model for software teams — from first idea to production. Three peer-supervised loops (discovery → build → release) over a catalogue of curated packs: skills, subagents, and hooks, each installed in one line. It's npm for your coding agent. Any agent, any stack — Claude Code, Codex, Cursor, Copilot, Gemini, Kiro.

observed-knowledge-ledger

Lessons your coding agent can trust: briefed before every task, proven by checks, and flagged when the code they cover changes. Works with Claude Code and any MCP agent.

jeffy-loop

Jeffy Loop is an autonomous software-engineering control system that forces an LLM to continuously audit, act, verify, checkpoint, and prove convergence.

llmtrim

Local proxy that compresses your LLM API requests so you pay less, with no change to the answers. Trims wasted tokens from prompts, history, tool output, and code before they're sent: -31% input / -74% output, measured live. Any provider, no extra model calls. Also an MCP server and embeddable library (Rust, Python, Ruby, Kotlin, Swift, JS/TS).

ait-native

Local-first task workflows for coding agents: bind intent, isolate work, verify changes, and trace their history.

maid-runner

A deterministic CLI for manifest-driven AI development. MAID Runner turns change requirements into enforceable contracts for planning, TDD, implementation, review, and validation—helping AI coding agents deliver disciplined, evidence-backed changes with less drift.

ai-context-core

Advanced static analysis engine for AI-driven development context management, project quality auditing, and specialized QGIS compliance.

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.

nerdit

Self-hosted PaaS for one machine: apps, local AI models and databases, operable by coding agents over MCP.

brnrd

A persistent, reachable resident behind Claude Code, Codex, Grok Build, steer it from Telegram/GitHub/WhatsApp, it keeps working while you're away. It opened >1K PRs on this repo. Self-hosted, $7 hosted.

nwave-ai

AI agents that guide you from idea to working code, with you in control at every step.

moai-adk

Agentic development harness for Claude Code — SPEC-driven plan/run/sync, TRUST 5 quality gates, model+effort routing, and Claude×GLM multi-LLM cost control. Single Go binary, 16 languages, zero deps.

grey-panda

The calm guardian for AI, agent, and MCP code — a zero-dependency, OWASP-anchored AI security toolkit.

paritok

Non-destructive compression gateway for AI coding agents. Cuts token bills 25% on turn 1 to past 85% in long or saturated sessions, and fits ~3× more turns in the same context window. Powered by our open-source code-native 4B model. Drop-in for Claude Code, Cursor, Codex, OpenHands, and any BASE_URL agent.

deepcode-hku

"DeepCode: Open Agentic Coding (Agent Harness & Loop Engineering & Multi-Agent Orchestration)"

maven-decoder-mcp

MCP server for inspecting, searching, and decompiling Maven .m2 JARs for Java AI coding agents.

org-knowledge-layer

Lessons your coding agent can trust: briefed before every task, proven by checks, and flagged when the code they cover changes. Works with Claude Code and any MCP agent.

pyllym

PyLLyM fun to build with Python LLM related things, just do it, build, and have fun doing so, switching models is easy.