Ai Coding Agents Python Packages

loki-mode-sdk

Autonomous software factory. Give it a GitHub issue, a spec or a one-line task; get back a pull request with a signed receipt anyone can re-check offline. Runs on your machine with your own keys: Claude, Codex, OpenCode.

wizolt

A terminal-based AI coding agent

agent-parley

Run Claude Code, Codex, Copilot, Gemini, OpenCode and Amp side by side in isolated Git worktrees, with shared issue ownership, reservations and explicit handoffs.

entroly-core

Cut AI context cost without trusting the compressor. Every reduction is reversible, byte-exact recoverable, and carries an auditable receipt. Local-first, works through proxy, MCP, SDK, or agent wrapper.

habit-hooks

Automated quality checks that nudge AI coding agents toward better habits

habit-hooks-generic

Automated quality checks that nudge AI coding agents toward better habits

entroly

Cut AI context cost without trusting the compressor. Every reduction is reversible, byte-exact recoverable, and carries an auditable receipt. Local-first, works through proxy, MCP, SDK, or agent wrapper.

openshard

Receipts for AI coding agents. See what ran, what changed, what was verified, and what it cost - across Claude Code, Codex, Cursor, and OpenCode.

habit-hooks-typescript

Automated quality checks that nudge AI coding agents toward better habits

habit-hooks-python

Automated quality checks that nudge AI coding agents toward better habits

cairntir

Local-first persistent memory MCP server for Claude Code, Codex, Cursor, Qwen Code, and AI coding agents. Cross-session, cross-agent SQLite memory.

true-memory-fragments

Prevent AI coding agents from acting on stale code context with source-aware freshness checks and hard stale gates.

minacode

A terminal-based AI coding agent

iac-guard-v

Verification framework and benchmark for LLM-generated IaC repairs. QRS 2026 regular paper. arXiv:2609.28488.

habit-hooks-java

Automated quality checks that nudge AI coding agents toward better habits

skeletongraph

Zero-LLM structural code retrieval for AI coding agents — tree-sitter index, BM25+dense+structural fusion, served over MCP.

thea-software

AI coding-agent verification — a machine-readable rulebook (atlas.yaml) telling agents which commands prove a change; the build fails when checks are skipped. 42 languages, CLI + MCP + CI.

habit-hooks-php

Automated quality checks that nudge AI coding agents toward better habits

arcgentic

Mechanical plan/dev/self-audit/external-audit gates for AI coding agents, with a configurable role-routing topology engine, an MCP-UI live status panel, and native-tooling Claude Code V2 dispatch. Claude Code, Codex, OpenClaw, and PyPI.

contextual-engine

Temporal-first local code memory for AI tools via MCP

nasde-toolkit

CLI for benchmarks & evals of AI coding agents — on tasks you already understand, using your Claude / Codex / Gemini individual subscriptions or API keys.

agent-feed

Turn AI coding chats into a source-controlled workflow: AGENTS.md, rules, skills, verification gates, and adapters for Codex, Claude Code, and Cursor.

ai-sdlc-framework

Declarative governance framework for AI-augmented software development lifecycles

agent-sessions-cli

Share Claude Code sessions with your team through git: /sessions:push, /sessions:pull, /sessions:init