Python agents

Keep AI-agent instruction files (CLAUDE.md, AGENTS.md, Cursor rules, Copilot) in sync from one source of truth, with a CI drift check.

The FastAPI of AI Agents — build production-ready AI agents, teams, RAG, and workflows from one package.

Simple ollama ai agent base for allowing a ai to run python functions

OmniAgentMemory — a namespaced, structured memory service for Claude Code and other agents

Haystack integration for openapi

Multi-model deliberation agent for OpenRouter Fusion on free models — CLI + MCP server for opencode

Local MCP gateway that proxies AI clients to many MCP servers with a token-efficient code mode

Tool-use agent with optional LLM brain via Ollama. Pure Python stdlib.

A lightweight debugger for RAG pipelines

Static security scanner for RAG pipelines

Reusable agent runtime package boundary

Optional Docling adapters implementing the runic.rag DocumentParser/DocumentChunker ports.

Drive the Claude Code CLI (`claude`) headlessly as a runspec runnable

Fault-tolerant streaming wrapper for the official OpenAI Python SDK.

Slack bot bridge to a local coding-agent backend.

Reserved name for the Spine family (RAG). Placeholder — see homepage.

LangChain VectorStore integration for VectorDB (Vektra)

Zespan observability middleware for Microsoft AutoGen

Agent IA d'audit technique de projets — analyse le code source et génère un rapport structuré en Markdown et PDF.

Isolated config launcher for coding agents (Claude Code / Codex / Hermes / OpenCode)

关系感知 Skill — 多 Agent 系统的社会层

Idiomatic, zero-dependency, provider-agnostic Python safety layer for AI agents: least-privilege permissions, prompt/input/output guards, sandbox + SSRF guards, quotas/rate/deadline/concurrency/risk budgets, loop detection, human-in-the-loop approval, constitutional rules, action previews, honeytokens, audit/tracing, and Claude/OpenAI/Gemini/MCP tool-call integration.

Local agent status reference implementation

Production reliability suite for LangChain/LangGraph multi-agent systems

Lightweight SDK for tracking AI agent costs and reliability with AgentAxon

Inline circuit breaker for LLM agents to prevent stuck loops, budget overruns, and output bloat.

A permission gate for AI agent tool calls. Stops dangerous actions before they execute. Safe under many concurrent agents.

CLI tools for agentharnesses.io

Make a FastAPI app agent-ready in one line.

Permission policy mediator for Claude Code, Codex, OpenCode, Gemini CLI, and Kiro.

Cut AI agent token costs. One line of code. Drop-in supervisor for LangChain, LangGraph, AutoGen, CrewAI, and Smolagents.

Chrome DevTools for AI agents — capture, view, and debug agent traces

Full-process autonomous scientific research agent — from literature search to LaTeX paper

An HTTP service that compiles Asymptote (*.asy) sources into rendered output (PDF, SVG, EPS, PNG, JPG).

Agent-native knowledge compiler — 27 CLI commands, 15 MCP tools, 10 domain packages. AI agents turn raw documents into persistent, cross-linked Markdown wikis with modular architecture, concurrency control, multi-provider LLM support, hybrid search, entity resolution, claims tracking, Louvain/Leiden community detection, grounded 'ask this wiki' QA, and contradiction-aware evidence confidence

Terminal-first local audit for AI security-agent traces: repeated tool-output work, stale replay risk, and JSON/Markdown receipts.

Python SDK for using an existing ChatGPT web session from Python and terminal tools.

Agente autônomo de programação via terminal com IA

DeepSeek AI Agent - 智能终端助手，支持 JSON 模式工具调用、文件精确编辑、后台任务处理、对话历史

Official Dial tools for the Microsoft Agent Framework — phone numbers, SMS, OTP, and voice calls

Official Dial AutoGen tools — phone numbers, SMS, OTP, and voice calls for Microsoft AutoGen agents

Official Dial CrewAI tools — phone numbers, SMS, OTP, and voice calls for multi-agent crews

Automatic image thumbnail generation for Django storages (local & S3).

Reliable, optimizable LLM steps with zero DSPy boilerplate

Autonomous coding agent — local-first, RAG-aware multi-agent CLI

A reactive declarative UI and threading utility library for exteraGram / Telegram plugins.

ForgeSight LangGraph adapter — auto-instrument LangGraph/LangChain agents via callbacks.

Franky - a lean personal coding agent that builds in a hardened container and opens a PR.

Haystack integration for google_drive

A clean, efficient framework for pretraining language models from scratch

LangChain tools for Hotdata runtime

LangGraph integration for Hotdata runtime

A simple CLI coding agent

夸父 (Kuafu) — 一个自我进化的 AI Agent 框架

LangChain embeddings that run on the Apple Neural Engine, via ANEForge (no CoreML).

BabelTele: model-native, high-density text compression for LangChain pipelines and agents.

LangChain integration for Infino — vector, BM25, and hybrid retrieval over one engine on object storage.

Library with a Tigris object-storage implementation of LangGraph checkpoint saver, with zero-copy bucket-fork branching.

LangChain Agent framework with built-in Web UI

Audit MCP server configurations for security risks

Anthropic component(s) as a standalone Langflow Extension Bundle.

Cohere component(s) as a standalone Langflow Extension Bundle.

ローカル LLM ゲートウェイ（local-llm-server / OpenAI 互換）に繋ぐ高レベルクライアント。エージェント共通のクライアントで、openai のボイラープレートを再実装しない（chat・画像・動画・音声認識/STT）。

Terminal benchmark runner with automatic discovery of local LLM servers

OBLIVION - Terminal AI coding agent with voice, RAG, and multi-model support. Powered by Meera.

Haystack integration for opentelemetry

Haystack integration for orcarouter

Project Agent Python CLI core

A lightweight, resilient, and production-ready evaluation engine to audit Retrieval-Augmented Generation (RAG) pipelines.

Haystack integration for Scavio Web Search

Non-blocking AI agent event logging for compliance teams

One command to make your codebase AI-agent ready.

Prime Agent CLI for Talos Protocol — autonomous GTM agents on BNB Smart Chain

The agent framework where the model never holds the trigger — every consequential action clears your policy first, waits for a human when it matters, and lands on a record you can verify. Build on it, or put it around the agent you already have.

Characterize the clients hitting a web site by analyzing its access logs.

Python runtime package for Agent Portal.

Tamper-evident audit trail for AI agents — EU AI Act ready

Repository environment-configuration control plane CLI

Reference Python implementation of the Agent Address Protocol (AAP).

Governance spine for AgentForge — identity (feat-029) and, as they land, registry / policy / audit drivers

Embedded, file-backed GraphStore for AgentForge (Kùzu)

Reserved - host-agnostic agentic-context engine.

A minimal, dependency-light kernel for a general-purpose AI agent — runs anywhere, brings its own brain.

A reliability harness for scheduled/autonomous agent systems: persist state across runs, prove liveness not just freshness, fail loud, and scan for the failure class before it ships.

Vendor-neutral event logging and redaction for AI agent workflows

The runtime-agnostic AI agent specification. Define once. Run anywhere.

A guard-railed harness that keeps wild agents in check - one gate, sandboxed, reversible context.

AgentProc Protocol SDK + CLI — connect any Agent CLI to a messaging platform

Python package for Agent Profiles.

Self-hosted AgentSave dashboard backend

AgentSave InferRoute — PPD append-prefill routing sidecar for vLLM / SGLang (Enterprise)

AI Agent Runtime Security Platform — runtime security and behavioral monitoring for agentic AI systems

Defensive overlay for AI agents — 8-layer architecture with harness-agnostic adapters; ships 6 of 8 layers (1 skill_vetting, 2 sanitize, 3 structured_output, 4 bash_guard+write_guard, 6 audit, 7 config) plus adapters for Claude Code (PreToolUse) and OpenClaw (before_tool_call)

LLM plugin for ai-mini-box — local and remote inference, RAG

Argus — AI threat-modeling agent (multi-agent, skills)

Axemere AI Gateway Anthropic SDK wrapper — drop-in Anthropic/AsyncAnthropic subclasses

Axemere AI Gateway LangChain integration — ChatAiGateway BaseChatModel

Axemere AI Gateway OpenAI SDK wrapper — drop-in OpenAI/AzureOpenAI subclasses

One-line spending control for AI agents. @budget(max_usd=10.00) decorator for LLM APIs and x402 payments.

Understand your Claude Code usage: token/cost/time analysis and a TUI over local JSONL transcripts.