Ai Coding Assistant Python Packages

codex-app-server-sdk

Codex CLI app-server python API client

trw-mcp

MCP server for AI coding agents — persistent engineering memory, knowledge compounding, and spec-driven development workflows. Part of TRW Framework.

code-context-control

Local MCP code-intelligence for AI coding tools: surgical search/read/edit, agent-config version history, path-level access + masking guards, and a multi-project hub.

agnix

The missing linter and lsp for AI coding assistants. Validate CLAUDE.md, AGENTS.md, SKILL.md, hooks, MCP. Plugin for all major IDEs included, with autofixes.

wizolt

A terminal-based AI coding agent

agentseam

The primitives layer for every coding agent — one handler API over per-agent hooks, instruction files, plugin packaging, and config.

personal-jarvis

Your AI assistant, built for the agentic era. Open source and local: talk to it, and it runs your agents, your coding CLIs, your browser and your apps. Windows, macOS, Linux.

factoryline-code-factory

Evidence-first audits for AI-generated code: prove tests can fail, catch security and release gaps, and ship reviewable receipts across VS Code, JetBrains, CI, MCP, and App Store workflows.

agentchanti

Autonomous multi-agent AI coding CLI & Python library with built-in RAG. Plans, codes, reviews, tests — works with local LLMs (Ollama, LM Studio) or cloud (OpenAI, Gemini, Claude).

jeffy-loop

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

drift-analyzer

Claude Code plugin that tells your agent when it is about to build something that already exists. Two-line install, no dependencies, answers in under 100 ms. Also a standalone static analyzer for structural drift.

seedcode-cli

Seed Code — a premium terminal-based AI coding assistant. Plant ideas. Grow code.

gito-bot

An AI-powered GitHub code review tool that uses LLMs to detect high-confidence, high-impact issues—such as security vulnerabilities, bugs, and maintainability concerns.

ai-code-review

An AI-powered GitHub code review tool that uses LLMs to detect high-confidence, high-impact issues—such as security vulnerabilities, bugs, and maintainability concerns.

vibepod

Unified CLI for running AI coding agents in isolated containers. Includes built-in local metrics collection, HTTP traffic tracking, and an analytics dashboard to track agent actions.

ai-cr

An AI-powered GitHub code review tool that uses LLMs to detect high-confidence, high-impact issues—such as security vulnerabilities, bugs, and maintainability concerns.

ast-outline

ast-outline lets AI coding agents pull exactly the code context they need — a repo skeleton, a file outline, or one symbol — instead of reading whole files. A stateless, tree-sitter-based CLI.

cli-agent-orchestrator

Multi-agent orchestration for AI coding CLIs — Claude Code, Kiro, Codex, and more, coordinated in isolated tmux sessions

roampal

Outcome-based persistent memory MCP server for Claude Code and OpenCode. Good advice promoted, bad advice demoted. pip install roampal.

memex-mcp

Persistent memory for AI coding agents via MCP: a bitemporal knowledge graph of your codebase, served to Claude Code, Cursor, Gemini CLI, and any MCP client. Tree-sitter and Gemini Flash into Neo4j via Graphiti. 14 MCP tools, hierarchical clusters, three-regime confidence decay.

founderealm-lens

A map for AI coding agents: three small files that survey a repository they have never seen and leave behind a SQL-queryable map of symbols, imports and call sites. Reads source, never executes it. Every answer carries the caveat that limits it.

paperpipe

Extract equations and context from research papers for LLM coding assistants (arXiv, LaTeX, RAG)

prusik

Deterministic, evidence-based build harness for autonomous coding agents — FSM sprint gates, execution-evidence verification, and adversarial critics. Proof, not opinion.

brasscoders

The bug scanner for AI coders. Local-first, deterministic CLI that catches the bugs your AI coding assistant misses. 12 scanners in one tool. Apache 2.0.