Python agents

LangChain toolkit for Attestify — governed AI loop execution, receipts, audit trails, and Attestify Trust (no-wallet agent identity + signed evidence)

LangGraph node integration for Attestify — governed AI loop execution, receipts, audit trails, and Attestify Trust (no-wallet agent identity + signed evidence)

Microsoft AutoGen tools to charge per agent task via U.CASH (HTTP-402). Non-custodial.

Reusable agent loop with multi-provider routing and MCP tool calling

Cellium Agent - 桌面 AI 助手

Convert ChatGPT web conversations into aidialog dialogs

Convert ChatGPT web conversations into aidialog dialogs

S3-like file storage using messaging platforms

A dairy-free RAG pipeline for delicious semantic similarity, clustering and NER.

Universal bootstrap framework for Claude Code projects

Local-first cost observability for Claude Code sessions

通过openai兼容的api代理运行claude code, 不修改claude code的配置

claudectl is now archeus. This release installs it.

Use several Claude Code accounts on one machine: hop the saved login in one keystroke, or run a different account in each terminal. One file, no dependencies.

A virtual co-worker that picks up Jira and Azure DevOps tasks and solves them with coding agents.

AI-powered documentation generator for Python projects

1500+ API connectors for Python and AI agents: catalogue, auth field schemas, OAuth2 and API-key connection management, plus scope-aware tools per connector. Sync and async

Gate any CrewAI tool behind human approval in Slack or Microsoft Teams, via AgentGate.

Amazon DynamoDB persistence backend for CrewAI Flows with built-in message pruning via agentstate-reducer

CrewAI tools for TranscriptAPI: fetch YouTube transcripts, search YouTube, and pull video metadata.

A custom ReAct agent using Groq, Tavily, Wikipedia, and a calculator tool.

Async FastAPI runner for DataRobot custom LLM and RAG models

Django storage backends and auto-configuration for Railway bucket storage.

Thin LangGraph node helpers for DMA memory.

Plug-n-play AI error-triage agent: captures Python tracebacks, has an LLM explain them, and reports to Slack + JIRA. Never auto-fixes — humans fix.

The /fastbuild agent: drives coding agents through a FastBuild task graph with AST-backed project memory.

Placeholder to reserve this name — not the real package.

CrewAI text to speech tool for the Gandr TTS API. First audio byte in 146 ms over the open internet, 116 ms p50 first audio, server side warm. 23 languages, every render watermarked.

LangChain text to speech tool for the Gandr TTS API. First audio byte in 146 ms over the open internet, 116 ms p50 first audio, server side warm. 23 languages, every render watermarked.

CrewAI tools for GateCore marketplace discovery, procurement, and governed execution

LangChain tools for GateCore marketplace discovery, procurement, and governed execution

JWT-gated LLM gateway: authenticate (bcrypt/JWT), then run a LangChain-on-Vertex Gemini completion. Unauthenticated calls are rejected.

Run a prompt through a LangChain (system + human) chain over Gemini on Vertex AI; optional LangSmith tracing.

Turn a prompt + a field schema into validated, typed JSON (Instructor over Gemini 2.5 Flash on Vertex AI).

Python toolkit for AI-assisted applications - an OpenAI-compatible LLM client, text processing, web scraping, and interactive demos

把 YC CEO 的思考方法变成你的 AI 助手

Autonomous AI agent that finds business-logic vulnerabilities (BOLA/IDOR, price tampering, workflow bypass, data exposure) — Oracle-verified, ~0 false positives

HexaLLM — AI coding assistant for the terminal

Policy-aware, provider-neutral agent runtime built on Pydantic AI

Reusable Jira → Claude Code → Spec-Kit specification toolkit

Wire LangGraph and CrewAI agents into Kafka-backed event-driven systems.

OpenAI Agents SDK recording adapter for Kitaru.

PydanticAI recording and replay adapter for Kitaru.

LangChain integration for 1Claw — HSM-backed secrets, signing, memory, and automations for AI agents

Gate any LangChain tool behind human approval in Slack or Microsoft Teams, via AgentGate.

Tool de LangChain para consultar LEX-MEX (leyes federales mexicanas con IA).

LangChain integration for Opensolr — managed Apache Solr with server-side embeddings and hybrid (BM25 + kNN) search

LangChain integration for PolarDB for PostgreSQL

Human-in-the-loop for LangChain agents — price-capped tools that delegate work to vetted human experts via Tendem, polling in plain Python (no LLM, no tokens) until the verified result returns.

AgentRAM-backed long-term memory for LangGraph and LangChain: a BaseStore plus agent-callable memory tools, no vector database.

LangGraph nodes/tools to monetize graph steps via U.CASH (HTTP-402). Non-custodial.

Endpoint-based evaluation harness for legal RAG systems

Bill LiteLLM LLM proxy calls via U.CASH pay-per-token. Non-custodial.

nvtop for llama.cpp: an interactive terminal dashboard for llama-server inference monitoring

Resolve llm model API keys from 1Password op:// references

Zero-dependency LLM call tracer — patch once, trace everything

A local, private anthology of every AI coding session — browse, search, spawn-tree, faithfully export and safely manage ChatGPT / Claude / Gemini / Codex history. No network, no egress.

Provider-neutral synchronous chat adapters for OpenAI, Claude, DeepSeek, OpenRouter, and LiteLLM.

Lightweight extraction of sglang's reasoning/tool-call parsers and chat template rendering for router services.

Local sidecar giving any tool grounded, cited, routed AI — Ollama or OpenRouter, no API key required.

Verify that LLM-extracted field values actually appear in the source document.

Share an LLM API quota across devices on a local network (Wi-Fi hotspot, USB tether, or LAN)

LLMTivo - record real LLM calls once, replay them forever, on the filesystem

Production-grade local semantic search and RAG framework

AgentLock authorization middleware for MCP (Model Context Protocol) servers.

LangChain retriever integration for MemStrata Conversational Memory

LangChain audit callback integration for MemStrata Governance

In-process llama.cpp VLM inference engine for MinerU

One minimal agent loop for SWE, web research, computer use, and delegation

CLI tool and MCP server for Mistral API with queueing and rate limiting

Mistral Harness

Agent supply chain security scanner.

Recommend, download, and run Ollama models based on your system specs and use case

A local-first, agentic shell for Ollama — chat, tools, and an MCP-style agent loop that never phones home.

GPT Image generation and OpenAI-compatible CLI by Ace Data Cloud

High-performance hybrid LLM inference engine with Adaptive Non-Uniform 2-Bit Quantization (Lloyd-Max + Fused Triton INT2 GEMM), RLM Context-as-a-Variable engine, 98.2% logit parity, and Zero-RAM quantizer.

Structured open atlas for Persian (Farsi) LLMs — manifest loader and CLI for researchers and agents.

AgentDuet transport for Pipecat: phone/WhatsApp calls in any Pipecat pipeline

A grounding-first RAG library: threshold-gated retrieval, concern-based chunking, a locked grounding prompt, and built-in faithfulness evaluation as the default path, not an optional rail.

LLM utils from the Princeton Robot Planning and Learning group.

The Operating System for AI Workers — build, deploy, and manage AI agents.

Azure CosmosDB backend for pydantic-ai-persistence — StepStore + message history for PydanticAI

Daytona sandbox capability for Pydantic AI agents

Amazon DynamoDB backend for pydantic-ai-persistence — StepStore + message history for PydanticAI

Google Firestore backend for pydantic-ai-persistence — StepStore + message history for PydanticAI

Backend-agnostic persistence for PydanticAI — chat history + durable StepStore, over a small async KV interface

Quality Assurance Operating System — engine-agnostic, documentation-driven, AI-native QA platform

LlamaIndex 기반 RAG All-In-One 라이브러리

An open-source, pip-installable Python library that quantitatively evaluates RAG pipelines using LLM-as-a-Judge methodology.

LLM-powered decision layer for the S2N web vulnerability scanner

Sophisticated Multi-Agent Orchestration System with infinite tools, cross-platform support, and TUI interface

Specify, solve, and simulate dynamic stochastic optimization problems.

Typed sync and async client for the Shared MDStorage HTTP contract

Local hybrid retrieval (BM25 + embeddings + RRF) for agent memory and codebases — one SQLite file, MCP server included.

An MCP which adds terminal capabilities to the Agentic framework.

Per-app developer agent for applications generated by Naviscom Shipyard.

SIQA Agent SDK for Python

A lightweight local CPU-optimized CLI executor agent via ONNX Runtime with safety filters

OpenClaw-like personal AI assistant MVP built with LangChain Deep Agents