Python agents

Bootstrap and maintain a Fumadocs-powered Project Atlas with agent skills, reusable templates, and validation.

JSON Schemas and Python contracts for AI agent memory integrity: evidence, candidate, ledger, taste, state, and ContextPack planes.

A virtual shell-over-database filesystem for AI agents: a strict, append-only memory layer with a frozen shell dialect.

Task routing layer for production AI agents — dispatch to the right agent by capability, health, and policy

AgentGuard — AI Code Security Scanner + Auto-Fixer

Lightweight Python client for the Agentic Trading Lab REST API (LLM-powered trading agents, backtests, paper trading).

Persistent memory for AI agents — store, retrieve, and recall context across sessions.

Agent-native event bus — connect agents, humans, and systems via typed events

Live observability and visualization for AI agent activity.

Collective knowledge store for AI agents — publish facts at runtime, query shared learning

AgentRelay Secure Memory Persistence and Recall integrations for AI frameworks.

AgentTrust Edge — the AI Agent Harness. One decorator, full trust enforcement.

A State-Aware Rollback and Trajectory-Replanning Framework for Autonomous LLM Agents

AgentSec-Bench: a security benchmark for LLM agents and harnesses, built on Inspect AI

Eyes for AI Agents — a machine-graded visual feedback loop coding agents consume to self-correct before claiming done.

Codex-safe Claude Code GLM-5.2 delegation wrappers.

Production-core policy scaffolder for GitHub Copilot agents in VS Code.

Production-core policy scaffolder for GitHub Copilot agents in VS Code.

Cross-session engineering memory for Claude Code + mattpocock/skills, powered by Memanto. Real lifecycle hooks + LLM distillation = zero repeated instructions.

Depot — 面向代码生成 Agent 的按需依赖解析系统

Agent and CLI to manage EC2 instances running self-hosted LLM inference: warm up an instance and serve an LLM, then hibernate it on idle to power ongoing inference workloads such as ADLC. Built on ec2-cli for the underlying EC2 machine lifecycle.

A simple, extensible package to manage file storage backends in FastAPI.

A deterministic, seeded synthetic-market sandbox that report-cards how autonomous LLM trading agents break.

FreshRSS API + MCP Server + A2A Server

HexaAgent — AI-UI-AI Loop für die GenesisAeon Architektur (Phase 6)

Use your ChatGPT Plus/Pro in Claude Code and other AI agents — one command setup

An integration package connecting Keenable web search and LangChain

Haystack integration for langdetect

Library to easily interface with LLM API providers

Async LLM backend abstraction with Retry-After aware clients.

A pre-spend GATE + learning advisor for LLM API cost: caps every call, prices from a verified table, and learns the cheapest config that keeps quality.

Search for anything using Google, DuckDuckGo, phind.com, Contains AI models, can transcribe yt videos, temporary email and phone number generation, has TTS support, webai (terminal gpt and open interpreter) and offline LLMs and more

LLM Attack Surface Mapper for AI Security Testing

Explainable human-like memory layer for AI agents.

Haystack integration for oauth

The official library for vLLM client network and preflight validation engine.

Grok 4.20's inference-time multi-agent chatroom, rebuilt from scratch — specialist agents debate via tool calls, a captain synthesizes.

OpenBB Agent Server: pluggable, multi-tenant agent backend wired to the OpenBB Workspace UI.

MemGPT memory architecture as a Python sidecar for the openclaw-memgpt plugin. Includes Anthropic/Claude compatibility patches against the original MemGPT (Apache 2.0).

Free OSS RAG library — ingest, graph RAG search, communities, bridges, append (API parity)

A lightweight toolkit for building secure AI systems with built-in middleware, protected memory, and AI safety models that mitigate prompt injection, jailbreaks, and adversarial attacks.

QUANT CLI 3.0 — Local AI Coding Agent with streaming, 12 tools, 6 modes

A context-aware, multi-level caching system for Retrieval-Augmented Generation (RAG) applications.

Framework-free backend RAG: deterministic dual-channel retrieval + agent orchestration with built-in anti-fabrication and source provenance.

Generate filesystem-based agentskills.io skill around a haiku-rag RAG database

Self-hosted, zero-trust RAG with role-based access control enforced at the database level

Find the best LLMs for your hardware specs

Sync CLAUDE.md with AGENTS.md for AI coding agents

Retrieval-Augmented Generation for Missing Data Imputation in Tabular Data

TIE storage client library

Haystack integration for Apache Tika document conversion

llm:// URI capability pack (vision/heuristic) for urisys-node

Zespan observability middleware for CrewAI

A SQLite-backed MCP server that gives your AI coding agents a shared memory bus.

Evidence-grounded evaluator for AI agent trajectories — judge by verifying claims against real tool outputs, not LLM-judge vibes.

Safe local document-to-markdown preprocessing for OpenClaw, Claude Code, Codex, Hermes, and other agents.

Real-time observability and auto-debugging toolkit for AI agents

Give your AI agent a signed, verifiable identity in one line.

Persistent Python runtime for AI agents

Workshop and scaffolding CLI for practical AI efficiency: learn core AI concepts, build your first agents, create useful CLIs, and adopt agent-first development patterns

Semantic diff engine for AI agent behavior — find the exact decision fork between two runs

Code Knowledge Graph (CKG) engine + agent toolset, built on AgentForge.

AgentForge — ReAct agents on open-weight LLMs with tools (RAG, REPL, web, SQL, calculator) and an eval harness. Pairs with ragforge-ml and turboquant-ml.

AgentMetrics - self-hosted AI agent observability server

Route Hermes delegate_task(background=True) to named, persistent AgentMint subagents.

Agent memory in a single SQLite file — no vector DB, no server, no cloud. Keyword recall on stdlib alone; torch-free hybrid semantic search via model2vec + sqlite-vec. Python lib + MCP server + CLI.

Track LLM costs across your AI agents

AI-powered observability SDK for Python applications

AISTV - AI IT Agent cho Windows

Financial statement PDF extraction agent

LangChain tools for Bolyra mutual ZKP authentication and SD-JWT delegation

A local application to feed images/videos from a webcam into local LLMs for analysis and conversations.

Slack message-turn bridge to AI coding agents (Claude Code / Codex / Copilot) running on your Mac

Call Claude Code from Codex for bounded, independent code review and second opinions

Sync your claude code sessions and memories in the cloud via Motherduck.

Turn a codebase, package, or doc into a valid Claude SKILL.md — offline, deterministic, and valid by construction. Optional Claude refinement. Zero runtime dependencies.

Claude Wiki - installable hooks and CLI for a personal knowledge base

Code Genie — a terminal coding agent (read, edit, and run your project from the CLI).

Call OpenAI Codex from Claude Code for delegation, review, and second opinions

CrewAI tool for Skim — clean web reader for AI agents. Card plan with API key (free tier) or x402 wallet pay-per-call ($0.002 USDC on Base).

Local CrispASR transcription workflow for Codex and MCP agents.

Single-file embedded database for AI agents. SQL + Vector Search + Full-Text Search + Hybrid Queries + Memory Graphs.

DataAgent - A powerful multi-modal Data Agent workflow template framework

Python interface to the Hall body-weight dynamics models, backed by the hallmodel-core C++ kernel.

AI-powered iOS test case generator supporting OpenAI, Anthropic, Groq, and GitHub Copilot

Agent-first guardrails framework for AI-assisted Python projects

INSPIRE HEP tools and API wrapper for LangChain.

LangChain tool for Skim — clean web reader for AI agents. Card plan with API key (free tier) or x402 wallet pay-per-call ($0.002 USDC on Base).

LlamaIndex reader for Skim — clean web reader for AI agents. Card plan with API key (free tier) or x402 wallet pay-per-call ($0.002 USDC on Base).

Keenable web-search and page-fetch tool spec for LlamaIndex. Keyless by default.

A mongo mcp that can be used to automate the database query with llm

Python SDK that fully drives the Mux-Swarm engine binary (stdio NDJSON + WebSocket).

Execution host agent for OneStep Control Plane deployments.

Typed MCP server for OpenAI Ads and ChatGPT Ads via the Advertiser API

LLM security middleware and risk analysis layer for prompt injection detection

Local-first RAG pipeline — PDF/Markdown ingestion, Qdrant retrieval, bge reranking, and an answer-quality eval harness. Pairs with turboquant-ml for quantized LLM serving.

RunAPI Gemini Omni SDK for audio, character, and video workflows in JavaScript, Python, Ruby, Go, Java, and PHP

RunAPI GPT-4o Image SDK for text-to-image generation workflows in JavaScript, Python, Ruby, Go, Java, and PHP

RunAPI GPT Image SDK for text-to-image and image editing workflows in JavaScript, Python, Ruby, Go, Java, and PHP