Python agents

LangChain tool integration for x402 web scraper with HTTP 402 micro-transactions on Base.

Yanez agent authorization: request human approval, verify signed receipts.

Open-source offensive security agents for autonomous pentesting

Evidence-backed project guidance and verification for coding agents

A small compatibility layer for OpenAI Agents SDK, Claude Agent SDK, and DeepSeek Harness

A process table for coding agent sessions. Claude Code, Codex, OpenCode, Hermes, Pi, CommandCode and Copilot in one view, with models, idle time, disk use and one key to stop them.

Deterministic audits of website readiness for agents.

Agent Resurrect SDK

Streaming FastAPI/ASGI adapter for an Agent Workbench service

Convert agent session logs (Claude Code JSONL) into Perfetto/Chrome trace JSON for ui.perfetto.dev

One permanent AI agent that builds, runs and retires other agents per task.

AD-001..AD-015: the agentic-dataset governance contract as language-neutral executable conformance vectors, plus a runner that needs no access to an implementation's internals

MCP policy gateway and red-team benchmark harness

Pluripotent stem-cell framework and universal agentic toolchain for autonomous workflows

An MCP which adds terminal capabilities to an agent.

Authorization and evidence SDK for AI agents: check permissions before every action, record what agents actually did.

Framework-agnostic observability, debugging, and deterministic issue detection for AI agents.

A framework for running AI agent workflows against code repositories.

HTTP and Telegram relay to agents-harness runner.loop (stdlib only)

Jailed terminal CLI for agent computer-use (policy + driver)

Five things an autonomous agent gets wrong silently, and the code that stops each one. Dependency-free stdlib.

Treat a whole git repository as a packaged, distributable agent. Where agents.md describes a repo to coding agents, agentsgit packages the repo itself as the agent: a manifest spec plus a CLI to declare, validate, pack, publish, and install repo-as-agent bundles.

Shared infrastructure library for the Agent Skill Forge platform.

Python SDK for the AgentSync x402 micropayment gateway on Radix

Ragas-inspired RAG quality evaluation, synthetic dataset generation, and continuous runtime observability for Agno.

Anthropic (Claude) LLM client for AI-Parrot (parrot.clients.anthropic)

OpenAI LLM client for AI-Parrot (parrot.clients.openai)

Schalter und Protokoll fuer die digitalen Mitarbeiter: Aufgaben zur Laufzeit an- und abschalten, Vorschlaege vermerken und ihre Trefferquote messen.

Haystack components and tools for AnyAPI: one key, hundreds of data and scraping APIs, billed per request in USD.

MCP gateway for AI agents to Robinhood Chain (Arcus DEX) tokenized US equities: quotes, multipliers, corporate actions, market status, sectors. Read-only, keyless.

Artis RPA remote execution agent — runs on target PCs

AutoGen extension client preconfigured for Hubris (https://hubris.pw)

Scan a drive, get a ranked inventory of what fills it, classified re-fetchable or not, diffed against last time -- before you delete anything.

An integration of Azure DocumentDB with Haystack

MCP server exposing Crispex, Perturbio and Bindigo as agent tools

Name reserved by BIT. The real package is bit-agent - https://osbt.space

Business-semantic driven AI agent configuration system. The missing layer between business users and AI agents.

The inter-agent communication protocol. Like HTTP for web services, but for AI agents.

The testing framework for AI agents — think pytest, but for agents.

Convert a human cell line identifier into a truth-track VCF of its known mutations.

Replay your own Claude Code sessions against a new model and see what actually changed.

MCP server that lets Claude Desktop delegate heavy work to OpenAI models: persistent sessions, file attachments, background jobs, live dashboard, cost tracking.

This is an LLM wrapper for claude and its subscription to use via Programming

Switch Claude Code API profiles with private credentials, settings backups, and history diagnostics.

Quota-aware failover proxy for Claude Code: spills over from Anthropic to Ollama Cloud when your quota runs low, and switches back once it recovers.

Finds idle AWS resources, proves they are unused, and plans a dependency-ordered teardown behind a human approval gate.

Extension vllm created by CME

A local CLI and MCP server for talking to configured AI models through LiteLLM.

Pre-execution gate for CrewAI: check an MCP server or package with RelayShield before an agent connects to it

Route a CTRLRun APPROVE through LangGraph's own interrupt().

Route a CTRLRun APPROVE through the OpenAI Agents SDK's tool-approval interruption.

A custom CLI terminal agent

An event-sourced runtime for durable, crash-resumable LLM agents

Готовый к запуску агент на базе ember: настройка в TOML, запуск одной командой.

Exact-action authorization receipt checks for Hugging Face smolagents tools.

Read a multi-source LLM context as the subspace it resolves, not as a centroid: locate prompt injections and off-source answers, with no trained model and no tuned constant.

In-process probe reporting what a Python workload imports and runs

llama.cpp plugin for flyte

Windows-first MCP server that gives AI agents the whole of GIMP 3: every PDB procedure, every GEGL filter, a render after each step, and repeatable recipes

Private local hybrid text and visual memory provider for Hermes Agent

A provider-neutral agent loop with extension hooks and typed tools

Manifest, registry and reconciler for every agent asset in the Kodemeio workspace

LangGraph-based production agent backend with a human-approval gate for effectful tools (Ops Copilot demo)

LangChain tools for AnyAPI: hundreds of data and scraping APIs behind one key, billed per request in USD.

LangChain tools for the Asterwise astrology API: natal charts, Vedic matchmaking with Rajju and Vedha vetoes, panchanga, Western natal charts and numerology.

LangChain tools that pay for HTTP 402 APIs over x402 instead of carrying API keys. Works with any x402 v2 resource; Ausca is the default example.

An integration package connecting Hubris and LangChain

Install LBrain into coding agents: native MCP, companion skill, fail-closed session start. The free name is generic. Make it permanent: https://lbrain.ai/claim.html

A package to combine GBNF and Beam Search for probablistic grammar pruning with configurables beams (both breadth- and depth-first)

llama-index tools anyapi integration

LlamaIndex tools that pay for HTTP 402 APIs over x402 instead of carrying API keys. Works with any x402 v2 resource; Ausca is the default example.

Register Anthropic-protocol-compatible providers as first-class llm models

LLM plugin for models hosted by Hubris

Regression testing for LLM applications (CI for prompts)

Task-oriented PDF conversion and review toolkit

Reversible PII redaction for LLM pipelines. Local, deterministic, no network calls.

An open-source, model-agnostic autonomous Agent SDK based on the ReAct framework

MaskFlow guardrail for LiteLLM: mask PII (Indian IDs included) before a request reaches the provider, restore it in the response -- streaming and tool calls included.

Public Python agent SDK for Matilda — agent lifecycle, streaming, client tool execution, human-in-the-loop, and multi-agent composition on top of matilda-client.

One SDK for MemStrata conversational memory and agent governance hooks

Lightweight, modular, hardware-aware LLM inference engine & empirical research testbed.

Interactive CLI for generating multi-agent AI project boilerplates.

Generic OpenAI-compatible inference provider for the NucleusIQ AI agent framework (vLLM, SGLang, TGI, llama.cpp, LM Studio, NIM, and OpenAI-compatible clouds).

LangChain Tool + Retriever for PixelRAG (screenshot-native visual search) — unofficial community integration

Official Anthropic Messages SDK adapter for PurrA

Official OpenAI Responses and Chat Completions SDK adapter for PurrA

Durable, fully-traced orchestrator that triggers any registered Pydantic AI agent from any channel and delivers results back through one uniform Trigger/Notifier interface.

One client for every OpenAI-compatible LLM server - local (Ollama, LM Studio, vLLM, llama.cpp) or hosted (OpenRouter, OpenAI) - with images and audio as plain message parts.

An inline hallucination gate for production RAG pipelines: atomic-claim decomposition, a cost-tiered detection cascade, and a configurable decision policy.

SRE reliability scanner for AI agents, MCP servers, and LLM tools. Scorecard + fix-it guide.

Autonomous Zero-Vector Memory Framework for AI Agents powered by Google Gemini & Biological REM Consolidation

Provider-agnostic classification and summarization for Render Workflows

An MCP Which adds the terminal capabilities to an agent.

Memory tools and middleware for Microsoft Agent Framework with Smaran

Memory tools and middleware for OpenAI function calling with Smaran

AI-assisted SOC alert triage and incident analysis toolkit

A self-funding analyst agent: earns on Stripe, fulfils with NVIDIA Nemotron, spends within guardrails.

Deterministic pre-deployment checks for AI agent systems. Blocks unsafe designs before they ship.

Sori, an audio language model agent. This name is reserved; the package is released together with the model.

Sori, an audio language model agent. This name is reserved; the package is released together with the model.