Python agents

Spool SDK for Python — trace LLM agent runs into the local Spool store

A Python Agent framework for multi-model access, tool calling, RAG, context engineering, evaluation, and Agentic RL.

Orchestrate AI agents from your terminal — multi-source credential import, swarm topology, background queue, live dashboard

Connect your agents to Trovis — two lines of code for full observability

ViLLM Fast Tokenizer — Rust backend with embedded SentencePiece for Vietnamese-English code-switching

A high-throughput and memory-efficient inference and serving engine for LLMs

A lightweight stateful agent framework with ReAct reasoning, tool dispatch, and MCP integration

Agent Passport Standard (APS) — Python SDK

Local-first verdict layer for AI coding-agent runs: graded repair receipts and a loop-gating exit code. No outbound network code; optional dashboard binds 127.0.0.1 only.

Native GTK4 GUI to manage and resume AI coding agent sessions (Claude Code, Cursor)

Self-hosted web scraping and Markdown extraction for AI agents.

CLI de testes E2E com IA: linguagem natural vira Playwright executável.

Agentok — placeholder package.

Async Python SDK for AgentOS APIs.

VietQR payment infrastructure for AI agents — AgentPay VN MCP server & Python SDK

Replay recorded LLM API traffic against a candidate model: cross-provider migration & regression reports (OpenAI/Anthropic/Gemini/Mistral) with scoring, cost and latency, built on httpx record/replay

Find and redact secrets in AI coding agent histories (Claude Code, and more).

AIGP Agent Governance Core — shared lifecycle for all framework adapters

AIGP governance adapter for LangChain/LangGraph

Drop-in replacement for the OpenAI Python SDK — routes to AINative's free Llama, Qwen, DeepSeek & Kimi API.

Lightweight LLM API security layer — deterministic, no AI, no DB.

Agent execution harness — wraps LLMs in structured, inspectable workflow specs

Autonomous QA Agent — scan, test, and fix any codebase automatically

Small Python library for invoking Claude 4.x models on AWS Bedrock with manual retries, prompt caching helpers, and JSON parsing.

Bridge MCP Agent

Typed graph-storage task adapter interface: the repository-style contract (CRUD, typed query execution, introspection) between graph-storage tool capabilities and the substrate.

MCP server that automates Claude Code conversation handoffs — no more manual copy-paste when you hit the message cap.

Always-on Telegram bot that drives the real Claude Code binary on your subscription — no API key, no Agent SDK.

Configure crewai to use AINative's free LLMs + ZeroMemory — no OpenAI key needed.

Wrap a deny.sh vault entry as a LangChain v1 tool. The credential resolves inside the tool boundary; only a narrowed DTO reaches the model. Fail-closed leak sweep.

Wrap a deny.sh vault entry as an OpenAI Agents SDK tool. The credential resolves inside the tool boundary; only a narrowed DTO reaches the model. Fail-closed leak sweep.

Dome Platform LangChain adapter — govern LangChain tools with Dome authorization

Moss semantic search retrieval module for DSPy

OmegaEngine governance integration for dspy-omega

Centralized Enablement Agent — the canonical knowledge hub for Partner Core enablement content.

Browser fingerprint consistency checker — UA, Client Hints, WebGL, timezone lint. CLI: fp-coherence.

Google Gemini SDK with OmegaEngine governance

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

A small, cheap hallucination / grounding detector — does an AI answer stay supported by its source?

HonorNet agent presentation client (MCP-first) — a protocol shim that mints proofs and presents three-part ADR-009 bundles. It decides nothing (hard rule 3).

Kyvvu compliance integration for Claude Code — policy enforcement via hooks

EMILIA Protocol guard for LangChain tools: a named human approves the exact irreversible action (Face ID / passkey) before it executes — fail-closed, with offline-verifiable Trust Receipts.

LangChain integration with OmegaEngine governance - callbacks, tools, and safety chains

Native LangChain / LangGraph tools for the Rine network — send, receive, discover, and run E2E-encrypted agent-to-agent conversations and groups from a LangChain / LangGraph agent

LangGraph checkpointer backed by PerSQL — durable agent state in an isolated SQLite database per agent.

Automatic model routing and deprecation handling for OpenAI, Anthropic, and Google Gemini

AINative provider for litellm — free Llama, Qwen, DeepSeek & Kimi models via one call.

llama-index embeddings voxell integration

llama-index tools MINT Protocol integration

基于 APScheduler 的异步任务调度通用库，支持 cron、interval 与 manual 触发模式。

LLM diagram generation library for Mermaid, PlantUML, and draw.io style workflows.

vLLM plugins for LLM-jp models

Large Language Model Processing Unit

Wrap installed coding-agent CLIs; capture traces, curate cross-session knowledge, serve a read-only viewer.

Mission working memory for LLM agents: session graph + pin_map, not a RAG corpus

MINT Protocol plugin for Microsoft Semantic Kernel — universal work attestation for AI agents.

Resumable multimodal-LLM annotator and embedder for folders of audio or image files.

A module to facilitate local testing of RAG pipeline for multiple datatypes

Okta CIAM/SSO MCP Server and Agent for Agentic AI!

OpenAI Agents SDK session memory backed by PerSQL — durable conversation history in an isolated SQLite database per agent.

Pentesty security monitoring agent

Plug-and-play RAG pipeline library for Python. Load, chunk, embed, store, retrieve, and generate — all in one clean API.

Backend of a system to explore RAG operations (formerly published as raglab)

Respan instrumentation plugin for AWS Bedrock Runtime

Respan instrumentation plugin for Cohere

Respan instrumentation plugin for LiteLLM

SportAgent: Multi-Agent LLM framework for Kalshi sports markets

AI-powered coding assistant plugin for Spyder IDE

Tenuo governance for Claude Code — warrants, hooks, MCP proxy, and Cloud lifecycle

Open-source runtime ROI diagnosis toolkit for AI Agent applications.

Vendor-neutral control plane for AI agents — governance, audit, and runtime enforcement.

AI travel agent MCP server - search flights, hotels, plan itineraries, optimize budgets. Import into Claude or any MCP-compatible AI.

Earned autonomy for LangGraph — evaluate, interrupt, approve, resume.

Earned autonomy for the OpenAI Agents SDK — warrantd drives the approval switch.

Youtube Autonomous FastAPI Docker Llama.cpp Module

Meta-package for the EmbedAgents embedded-development tools for Claude Code. Installs the whole family; each tool also installs individually (embedagents-stm32, ...).

Agent-Bioinformatics Interface: plugin-based abstraction for AI-driven bioinformatics analysis

轻量级个人助手 Agent CLI — 集三大开源项目设计思想之大成的融合实现

Microsoft Agent Framework conversation history backed by PerSQL — durable message history in an isolated SQLite database per agent.

MCP server for best-of-Agent-Harnesses: opinionated harness recommendations (recommend/pick_harness), search, and head-to-head decision guides over a hand-curated, weekly-rescored list of agent harnesses

Visualize Pydantic AI agent workflows from Logfire traces as an interactive HTML diagram.

MCP checkpoint server: atomic state coordination for AI agents, cron workers, and multi-agent systems

Build AI agents for phone and WhatsApp calls with real-time audio and messaging

CVE-style advisory database and static scanner for AI agent security risks

Pre-execution budget enforcement for agentic AI workflows

Reliability and reproducibility statistics for stochastic agent / tool-use evals.

TRACE conformance test suite

Observability and proof reporting for AI agents

Arabic-first Retrieval-Augmented Generation (RAG) toolkit with local-first fallbacks

Add your description here

Expose AstrBot agents as MCP tools via CLI

A framework-free agent runtime you can read, run, and leave. Own the loop, not the framework. Runs local on Ollama at $0 — or any frontier model.

Trace cross-file dependency blast radius with GitLab Orbit, before you break things.

Composite Grounding Score: multi-signal hallucination detection for production RAG systems

Token economy and workflow stack for Claude Code

Local D365 F&O knowledge toolkit: corpus indexing (SQLite FTS5), deterministic generation, and an MCP server that grounds coding agents (Claude Code, Codex) in real AOT facts.

Local D365 F&O knowledge toolkit: corpus indexing (SQLite FTS5), deterministic generation, and an MCP server that grounds coding agents (Claude Code, Codex) in real AOT facts.

Reusable agentic primitives extracted from DataForge.