Python agents

Official Python SDK & Local-First RAG Memory Engine for AI Agents

ECO AGENT - Five-layer loop driven autonomous AI agent system

Evaluation-Driven Development (EDD) tools and helper libraries for AI Agent development

Use Eden AI with Haystack to build AI applications with 500+ AI models through one unified, OpenAI-compatible API.

An OpenAI-first agent harness core for controlled, durable, and observable agent runtimes

Multi-platform AI agent for the terminal and messaging apps — part of the AiUtils.io ecosystem, powered by Elidia Technology

Python SDK for the ELLM Guardrail — deterministic policy firewall for AI agent tool calls

Customer accounts export from Django Accounts to Magento via the Magento REST API

Export of Volkanos checkout orders, payments and shipments to the Magento 2 API

Import of order statuses from the Magento 2 API back into Volkanos checkout

Products, prices, pictures, and attributes export from PIM to Magento via the Magento REST API

ethical, local-only inference wrapper for llama.cpp

QUAlibrate connector for eTiKeT sync agent

AgentLab — a modular framework for building, evaluating, and comparing LLM-powered agents.

LLM evaluation framework for developers

Composable RAG evaluation library for experiment-based testing

🦙 Exposed Ollama Instance Hunter, Proxy & API Manipulation Tool

Smart storage engine with data-type routing, multi-tenancy, and schema enforcement

Relevance-driven CPU KV-cache offload policy for stock vLLM

FableForge Agent — a fork of Hermes Agent (NousResearch). A self-improving AI agent that creates skills from experience, improves them during use, and runs anywhere

Unofficial OpenAI-compatible HTTP bridge for Factory Droid

Fairness definitions and bias metrics for large language models

Autonomous Limitless Exchange agent — Falcon signals, HMAC execution via Falcon API

Autonomous SX Bet sports agent — Falcon signals, local EIP-712 execution

An opinionated FastAPI framework for AI/agent production applications

A typed FastAPI server compatible with LangGraph RemoteGraph clients

An OpenAPI-native API agent and embeddable FastAPI assistant.

Mixed-precision LLM acceleration: faster with same output

A practical PRAGMA model implementation for tokenized tabular event histories

Python SDK for AI agents to take and repay revenue-underwritten credit on Fianza (Stellar). Settles in USDC.

Gate LangChain tool calls behind a Fidacy verdict. Wraps the tool itself, so a denied payment never executes: callbacks can only observe, this can stop.

A flake8 plugin that warns about expiring LLM model IDs

Google Cloud Storage for Flask

Configurable LangChain agent core for voice applications with pluggable domains, prompts, tools, and RAG documents.

Deploy LLMs to Kubernetes.

A functionnal oriented Python CLI for LLM calling with multi provider and multi model

FlowJet (fj) — one-shot CLI coding agent powered by soothe-nano

A Python-first Agentic AI Framework — provider-agnostic, async-first, middleware-driven

Run Claude Agent SDK agents on Flyte.

Shared contract for Flyte agent-SDK adapters.

Run CrewAI agents on Flyte.

Run LangChain Deep Agents on Flyte.

Run Google ADK (Agent Development Kit) agents on Flyte.

Run Hermes agent on Flyte.

Run LangChain agents on Flyte.

Run LangGraph agents on Flyte.

Run Mistral Agents (Conversations API) on Flyte.

Run OpenAI Agents SDK agents on Flyte.

Run Pydantic AI agents on Flyte.

Epistemic foraging for AI agents and researchers: source discovery, evidence pinning, uncertainty-aware briefs.

ForecastAgent 1.0: Zero-shot and fine-tuned time series forecasting SDK & CLI wrapper

Predictive cost, policy, and runaway-session guardrails for AI coding agents

fourotwo Python SDK for automatic layer402 payment handling

Async & Sync API client for FragAPI

Tool to generate a changelog from changelog fragments

AgenticOps stress-search harness: deterministic GA/MC over modular simulations, BYOW adapters, replay JSON, and FEL evidence semantics.

Extract, visualize, and inspect molecular fragments (fingerprint bits) shared by molecules within a class

Unofficial async client for Fragment.com, TON payments and Telegram gifts

Measure your brain's fragmentation tax — context switch tracking for knowledge workers.

A lightweight node-flow runtime for building tool-using agents. Import name: agent_core.

Agent orchestration layer for Friday Framework

LLM inference layer for Friday Framework

Agent-native CLI for Google Analytics 4

Small GB10/GX10 helpers for loading LLMs without slow cold-page CUDA H2D transfers.

Unofficial Python client for Google Gemini Notebook (formerly NotebookLM) - alias of gemini-notebook-py.

Unofficial Python client for Google Gemini Notebook (formerly NotebookLM) - canonical distribution from 0.9.0.

A Python package for automating Google Gemini web UI via Playwright

Canonical PyTorch implementation of Gemma 4

Decision-oriented agent runtime with explicit approvals, inspectable history, optional independent checking and a built-in web UI.

A placeholder package that reserves the name genericagentctrl.

Claude on Genkit

Ollama on Genkit

OpenAI-compatible models on Genkit

Python library to support LLM testing.

Declarative AI agent framework — MCP for tools, A2A for agents, AG-UI for humans

GEODE — 범용 자율 실행 에이전트

A modern multi-repository GitHub TUI with Claude Code integration

A spec-driven development PM agent that orchestrates multiple coding CLIs using GitHub Issues as state

Sync all your local projects to GitHub automatically

A glass-box, minimal library for building LLM agents — modern techniques as opt-in primitives, no hidden control flow.

Production runtime and network client SDK for Glyph

Google Cloud Agentidentity API client library

Google Cloud Agentregistry API client library

PyPI Package for Circles google-drive--storage-local Python

Google-OAuth-gated LLM gateway: verify a Google ID token, then run a Gemini (Vertex AI) completion for the verified caller.

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

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

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

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.

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

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

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

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

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

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

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

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

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

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