Python agents

Graph-first multi-agent orchestrator for Claude Code - parallel task graphs, hook-written checkpoints, ask-first resume, right-sized model tiers

Ray-native context/memory sharing for parallel research agents, with an agent-native CLI and MCP server (Milestone 1 spike)

Deny-by-default command safety gate and text-ReAct routing agent for small LLMs

Literature-validated Artificial Bee Colony optimization for Python

Time-shaped coordination primitives for swarm-anchor: predict-and-confirm, deadlines, rate limiters, BPM clocks, cron, and DAG-ordered campaigns. Stdlib-only Python.

Deprecated standalone compatibility package for chebyshev distance.

Deprecated standalone compatibility package for chi-squared distance.

Deprecated standalone compatibility package for cosine distance.

Deprecated standalone compatibility package for euclidean distance.

Deprecated standalone compatibility package for haversine distance.

Deprecated standalone compatibility package for jaccard index distance.

Packaged dummy filesystem skill for Swarmauri tests.

Packaged dummy local skill for Swarmauri tests.

Filesystem-backed skill loader for Swarmauri.

Local skill-root resolver for Swarmauri.

Load- and chaos-testing framework for AI agent orchestration plumbing

fsspec backend for Ethereum Swarm (bzz://) via the Bee HTTP API

SwarmGraph SDK: deterministic multi-agent orchestration primitives

SwarmKit web portal — the static Next.js build, served by `swarmkit serve`.

Verifiable serverless SQLite hosting on Ethereum Swarm: a read-only VFS over swarmfs plus a publish helper

Shared-context and memory coordination server + CLI for swarms of parallel AI agents, speaking the SwarmMesh v1 protocol (HTTP + WebSocket + MCP), interoperable with the Node implementation.

A living task graph for agent orchestration on Google Cloud. Reference implementation.

Local coding agent built on LangChain Deep Agents (LocalShell, no sandbox)

The self-improving AI agent — creates skills from experience, improves them during use, and runs anywhere

TAAR — Thirsty's Active Agent Runner: a local-first governed agent taskforce for Project-AI, with a GitHub Workflow Guardian.

Ternary Additive Contrastive LLM — CPU-friendly integer neural network

A plain-English terminal agent that plans and runs shell commands for you.

Autonomous AI coding agent driven by Markdown config — DeepSeek-ready, CLI + Web UI, 45+ tools, self-hosted

Ready-made agents for the TAI ecosystem — coding/deep agents, tool-calling, retrieval, voting, refinement, and vision agents — opt-in and manifest-loaded.

GitHub-backed Storage provider (text + binary/media) for the TAI ecosystem.

Local-filesystem storage backend for the TAI ecosystem: a manifest-loaded Storage plugin serving text and binary content from a directory tree.

S3 storage backend for the TAI ecosystem — text, binary, and media content over an S3 bucket.

TAPM v2 hook for Anthropic (in-process library instrumentation)

TAPM v2 hook for CrewAI (in-process library instrumentation)

TAPM v2 hook for LiteLLM (in-process library instrumentation)

TAPM v2 hook for OpenAI Agents SDK (in-process library instrumentation)

Self-hosted event server that pushes a notification the instant a parallel coding-agent session blocks, needs review, fails, or finishes.

Subagents extension for Tau (a port of pi-subagents).

Local execution daemon for Tether Brain agent installations

Temporal decay weighting for RAG. Rerank retrieval by similarity x document age, with adstock-derived decay kernels.

Deterministic governance filter for Semantic Kernel — function-call authorization, PII scanning, cost budgets, and structured audit trail.

Unified Teamver SDK for agent runtimes (channel, DM, drive, events, jobs, mail, agent tools)

Teamver Mail BE client for AI agent runtimes (inbox, events, processing, reply)

TechTide Swarm 357 — layered orchestration, durable memory bridge, and observability hooks.

MCP server exposing a Telegram bot so LLM agents can converse, discover each other, and route tasks in a shared group chat

Anthropic integration for telemetry.dev Python SDK

AWS Bedrock integration for telemetry.dev Python SDK

LiteLLM integration for telemetry.dev Python SDK

OpenAI integration for telemetry.dev Python SDK

Report from inside your app to TellMeWhenDown — cron heartbeats and self-checks in one line.

Time-aware semantic LLM cache — automatically invalidates stale AI answers

Prebuild import for storagegrid

Agentic framework for building and deploying AI agents with flexible orchestration, custom tool integration, RAG, Text-to-SQL, webhooks, and billing.

Add your description here

A secure, provider-independent coding agent for the terminal

THEMIS — Retrieval-grounded LLM for Indian statutory law (BNS, BNSS, BSA, IPC, RTI)

Repository-owned agent skills that just work

WhatsAI — deployable AI customer service agent by Tisement Media. Connect LLM + WhatsApp webhook and serve 24/7.

Local HTTP control daemon for tmux-backed coding-agent sessions

A small example package

A small example package

Mask PII in LLM tool-call outputs before they reach the model, with role-based access control. Zero dependencies.

An open-source improvement loop for production AI agents.

交易罗盘: local-first A-share trading agent workbench for short-term trading, ETF rotation, simulation, review, and memory-driven improvement.

Add your description here

Official Python SDK for the TruAgents Unsubscribe API.

Library to systematically track and evaluate LLM based applications.

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

Pi-style LM authentication helpers for DSPy

Connect your own AI to The Social Experiment: your agent thinks on your computer

Xberg document extraction and chunking pipeline for txtai embeddings

UI 自动化测试 Agent

A universal agent for reasoning over browser, desktop, and mobile UIs and performing actions on them.

A pure-Python (+numpy) byte-graph that is a 1-bit (ternary) LLM: dunder API, autograd, ultra-edges, visualization.

Shared memory and skills across Claude Code and Codex

Lightweight CLI + TUI agent for local and cloud LLMs with real tool calling

Configurable storage providers for unlib.

An integration of Upstash Vector with Haystack.

Universal Repository Agent Graph: structure-aware, token-efficient RAG for projects

Canonical LLM-facing URI process runtime — spec, executor, CI gates

URL technical footprint analyzer with GDPR & security-focused GenAI reasoning

Local-first agentic trading AI agent with on-device Pilot Router

A maintained successor to user-agents: identify devices (phones, tablets) and their capabilities by parsing browser user agent strings.

An MCP which adds terminal capabilities to an agent.

LangChain request-signing adapter for the VAID standard: sign every outbound agent HTTP request with a VAID proof-of-possession via a thin httpx.Auth seam.

A friendly Python wrapper (sync + async) around the Vapi voice AI API.

Self-hosted, MCP-first RAG backend over Obsidian vaults.

Local DLP reverse proxy for LLM traffic

IoT agent for vending machines: listens to the MDB bus and reports every sale to Vending Zets

AgentKit action provider for VeraData — LATAM sanctions/KYB screening for autonomous AI agents, paid via x402 on Base

Type-safe Pydantic wrapper around Vercel's agent-browser CLI

Hardened single-node registry service for Agent Auth identities

Python SDK for agent identity publishing, signed messaging, and registry-based verification

A veto gate for AI-written code in LangChain / LangGraph — 17 reality gates + frontier review, with veto power. Free to try, no signup.

Production-grade self-hosted document ingestion and retrieval service

VinOperator

LangChain integration for viparse — read Vietnamese documents, legacy encodings included

LlamaIndex integration for viparse — read Vietnamese documents, legacy encodings included

Compile CSV/XLSX data and DashboardSpec into validated offline HTML dashboards.

Out-of-tree bitsandbytes quantization plugin for vLLM