Python agents

LangChain vector store integration for Typesense

LangChain tools for U.CASH agent monetization over HTTP-402.

Python tools for Webz.io News Search - global news in natural language with semantic ranking and rich filters

LangChain retriever integration for YouTube — search videos, fetch playlists, extract transcripts, retrieve video metadata, and fetch comments.

LangGraph checkpoint saver backed by local filesystem, GCS, or S3 via fsspec

A bring-your-own-model LLM assistant service for Plaid IGT projects

一个基于 Textual 的终端 TUI 编码 agent

Browse and resume local coding-agent sessions

Simple & fast trufflehog secrets scanning for LiteLLM

llama-index retriever for AlletraMP X10000

llama-index tools gandr integration

Official LlamaIndex BaseToolSpec Integration for OpticParse Vision Web Scraping & PhishVision Threat Detection

LlamaIndex tools for StackResolve: find, compare, and audit software for AI agents, plus structured company research.

LlamaIndex tools for Truth Bear GAUGE official-source signal data

Python tools for Webz.io News Search - global news in natural language with semantic ranking and rich filters

LlamaIndex vector store integration for the Rostam vector database

Run local llama.cpp servers from a config file, and work out which model to run and how

MemorySync memory for LlamaIndex: a Memory subclass with durable server-side long-term memory, a recall memory block, a retriever, and agent memory tools.

LlamaIndex tools for U.CASH agent monetization over HTTP-402.

Official xAI Responses API package for llm-api-adapter

Concurrent, caching, retrying OpenAI-compatible batch chat-completion runner with structured output validation.

A local proxy circuit breaker to stop runaway AI agents from burning API budgets.

Deterministic pre-filter + cheap→chief escalation pipeline — send only the few items that matter to your expensive model.

Audit the attack surface of a machine running local LLMs (Ollama, LM Studio, vLLM, llama.cpp...). Stdlib only.

LLM plugin for models served by oMLX

LLM plugin for models hosted by OpenZoo - no signup required

Put one question to several LLMs independently and read every answer in full -- parallel judges, failure classes, cost, and an anonymised rebuttal round

Data-only defensive playbooks and canonical offline advisory policy pack.

Local AI traffic privacy gateway — mask sensitive data before it leaves your machine

Evaluation pipeline for LLM watermark detection experiments

Practical local LLM evaluation on real hardware

Read-only CLI and TUI over the generated llms-explorer concept tree and llms-concept-abstractor concept packs, plus a thin CLI over the skills SDK

Server-side SDK for tracking LLM token usage, costs, and observability data in LLMtrack

Local-first hybrid RAG for Markdown and Obsidian knowledge bases, with CLI, MCP, and Hermes Agent integration.

Universal Multi-Agent Ecosystem for Lorapok Labs — 224 Autonomous Agents, 20 MCP Servers, and 6 Formations

Native Tokitai runtime bindings for the mathdatiao competition agent

MCP server that calls a local Ollama or vLLM model for language work, with schema-validated JSON output checked by a dependency-free validator.

Médiathèque agent: scan, fingerprint, dedupe, and compress local media libraries

Local-first layered memory and autonomous learning engine

OCI Distribution object adapter for Meridian

OpenSearch adapter for Meridian V1 multilingual search projections

Valkey adapter for Meridian V1 disposable key-value and cache semantics

A zero-dependency, ultra-lightweight state machine for building agentic AI workflows without heavy frameworks.

Library for building agent tests using Microsoft Agents SDK

PostgreSQL + pgvector backend for mistralai-search-toolkit

Cross-platform local MCP server and CLI for bitemporal long-term memory for AI agents

An AI Agent for Mood and Sentiment Analysis in Python

Archive local AI chat histories to S3, freeing up disk space while keeping conversations searchable

Unified detection, configuration, and chat discovery registry for AI coding agent CLIs

Multilingual RAG MCP server — cross-lingual search over local documents

Murage — agent orchestration platform. Name reserved; implementation in development.

Deterministic local MusicXML engine and Claude Code Agent Skill

Remote agent adapter for NeMo Fabric

Agent-first CLI for controlling Notion: pages, databases, blocks, and search. Also a communication lane — other AgentCulture agents use their own CLIs and skills to talk to each other through shared Notion pages and databases.

A deterministic runtime for capability-aware agent execution

nuagent: the model answers in Nu, Nu runs the answer.

Integrate automation with OpenAI/LiteVLLM Api

Allows to use server environment with storage backend FTP

Allows to use server environment with storage backend SFTP

Allows to use server environment with storage file

Odoo JSON-RPC CLI and Python client built for AI agents and scripts.

An open-source local coding assistant powered by Ollama.

Onyx Gate for CrewAI — a verifiable authorization gate for crew tool calls: policy-decided allow/deny before a tool executes, with an audit trail you can re-check.

Official Python SDK and fleetctl CLI for OpenAgentFleet — self-hosted autonomous computer-use agents, each with its own Linux desktop

Use the Codex CLI's ChatGPT login (~/.codex/auth.json) as a bearer credential for the Codex backend

Session collection for AI coding agents — reads what agents write to disk and normalises it into one session model.

A response model for calculating the climate impact of air traffic emissions

Company fundamentals from official filings, dated by filing, from tradingagentapp.com for the OpenBB Platform (US SEC EDGAR, Japan EDINET, Taiwan TWSE, Korea FSS OpenDART, France INPI, Belgium NBB, Denmark Business Authority, NZ Charities Register).

The lifeforce kit: give any agent an identity, a home floor, a memory, a governed mind, and a diary — and it appears in the universe.

Haystack integration for Parallel web search and web-research models

Broker-agnostic messaging layer that lets AI agents (and humans) on different machines talk in named rooms and wake each other.

Framework-agnostic RAG middleware that makes any pipeline self-improving via persistent failure-pattern memory.

Multi-agent LLM peer-review framework (an editorial board for manuscripts)

Gerenciador do protocolo PEP-Agentes para Claude Code e Codex

Reservierter Name — defensiver Platzhalter der PflegeAnwalt-Plattform, nicht installieren

MCP local de découverte et sélection déterministe de skills validés.

A tamper-evident, hash-chained audit ledger for AI agent actions.

Standard ACP agent over AgentHarness (no x.ai extensions)

Connect a voice agent to the TeleCMI telephony platform

Drag files found on the command line into any app that accepts drops

Fake AG-UI agent backend for testing. Deterministic scripted event streams, session record & replay, failure injection. No LLM needed.

Lightweight, hardware-independent local GGUF parser and Ollama substitute server with Hugging Face Hub integration.

Automated AI Pull Request Reviewer & Security Code Auditor.

Static dead-code analyzer for Python projects

Autonomous Security & Zero-Trust Governance Guardian for Enterprise AI Agent Fleets by Prema AI Labs

A deterministic evidence gate for coding-agent completion claims.

Permissioned coding-agent CLI with durable planning and isolated execution.

LiteLLM provider backend for purrcept_core.

Open-source policy engine for agentic payments

Packaged Carta service agent binary and utilities for pycarta[service].

MemorySync memory for Pydantic AI: a drop-in agent capability that injects recalled context every run and sends each completed run's user prompt to fact extraction, plus typed memory tools and async helpers.

Speak pydantic-ai streamed output aloud, as it streams

Run Pydantic AI graphs with durable Waymark model and tool actions

Harness, loop and graph engineering for production AI agents.

Regression tests for AI agents. Record once, replay offline, catch behavioural regressions.

A lightweight, hackable mini-OpenCode written in Python.

Runtime-scoped LLM hooks for verified Python handlers and source patches

Gate every LangChain agent action through Qerexa runtime trust enforcement.

MCP servers extracted from the trading swarm: point-in-time data, pre-trade invariant + leakage audits, regime-fragility probes, and the Shadow Tournament bridge that scores your genome against the swarm's live champion.

Independent multi-harness, multi-model agent tools for quant_trade