Python

AgentTrace is a Python-based observability and runtime self-healing system for AI agent workflows. It logs multi-step tool calls, surfaces latency issues, and attempts to repair malformed LLM tool arguments before they crash a run.

A Go-based CLI for managing Python virtual environments, with MCP tools for AI agents, typed JSON snapshots, ephemeral execution, and file-watcher sync for evolving scripts.

A Python-based coordination protocol and daemon for running multiple LLM sessions in parallel with shared awareness, aimed at Claude Code and other Anthropic-compatible models.

A migration guide for the OpenAI Python SDK explaining the move to HTTPX2, including default client behavior, TLS trust store changes, custom client setup, timeouts, transports, auth hooks, and streaming/response handling.

A cross-platform CLI for monitoring live Claude Code sessions, context usage, models, and spawned subagents.

An agentic LLM-based coding tool that analyzes symbol names in source code, measures name ambiguity, and proposes clearer replacements with a human-in-the-loop review flow.

A Python CLI and research toolkit for simulating AI training math before model training. It estimates memory, training time, token budget, config risks, benchmark speed, and reliability, with optional native Rust and C backends.

vid-line is a CLI tool that turns videos into ANSI art and plays them in the Claude Code statusline. It supports YouTube URLs or local files, includes install and usage instructions, and explains how playback works and how to resize or switch videos.

An experimental programming language and compiler designed for LLM-written code, with a Python-based toolchain that compiles to native macOS binaries. The repo also includes a full NES emulator written in Laze and usage examples for both the compiler and emulator.

Rapunzel is an open-source desktop app for managing agent sessions in a tree-style terminal interface. The README explains its purpose, install steps, launch commands, build instructions, and the core features: branchable terminal sessions, workspace persistence, and session management actions like rename, move, collap

Windows desktop chat client for OpenRouter with streaming completions, model browsing, multi-session history, local storage, and PySide6 UI.

Python CLI wrapper for Jev that analyzes JSON, NDJSON, JSONC, and text logs with typed AI questions and confidence-aware answers.

A Python library that traces multi-step AI agent workflows and compiles repeated trajectories into deterministic, low-latency code with runtime guards and fallback to the original agent.

Ramanujan is a terminal-based multi-model agentic workbench for research in computational mathematics. It lets users chat normally, break down problems, survey literature, run parallel subagents, and produce a consolidated report with deterministic checking via SymPy and Z3.

A lightweight SQLite FTS5 memory layer and MCP server for Google Antigravity agents, with CLI tools for storing, searching, and syncing facts.

A Python tool manager for AI agents that uses an LLM-tools.txt registry to install, pin, describe, and execute tools with one predictable contract.

Python library that automates ChatGPT and Gemini through the web UI, using a real Chrome browser to send prompts, upload files, and return responses as Python objects.

A lightweight, cross-platform offline desktop AI assistant with local-first features like inline writing help, memory vault, command safety checks, meeting notes, and file-based RAG.

Search2o is a Python package for running searchable AI agents inside an organization, with a REST API, bundled GUI, and support for self-hosted or vendor LLMs.

Public evaluation code for an Agent Memory Leaderboard, including answer-generation and scoring contracts for comparing LLM agent memory systems.

A side-pane companion for Claude Code that shows daily AI news and spaced-repetition concepts while the agent is working, then hides when it needs user attention.

A drop-in memory plugin for Hermes Agent that uses a pull-model episodic memory approach with real deletes and audit traces. It supports synchronous writes, trace logging, and Claude-backed summarization for on-demand recall.

A technical tutorial that walks through building a coding agent in Python, including tool calling, file editing, shell execution, web search, and permission prompts. It includes code snippets, a demo workflow, and a linked GitHub repository with the full implementation.

Pull request adding TY25 support for moonshotai/kimi-k3 in TaxCalcBench through OpenRouter. The snapshot shows benchmark wiring, PDF handling details, saved outputs and evaluation reports, and regenerated charts/results for the full TY25 set.