PyPI agents

Placeholder for the TogoAgent multi-agent framework.

LangChain-powered intelligent agent for Token Bowl Chat servers

A lightweight library for generating short-term bearer tokens for AWS External Anthropic API authentication

Token Shift GPT - Pytorch

AI coding assistant with pluggable tools and token tracking, built on OpenHands SDK

LangChain Runnable client for TokenCrush prompt optimization API (/v1/crush)

Query-aware semantic chunk selection under LLM context-window budgets.

Name reserved for the tokenspeed-trtllm-attn project.

Name reserved for the tokenspeed-trtllm-common project.

Name reserved for the tokenspeed-trtllm-gemm project.

Standalone TensorRT-LLM CUDA kernels as PyTorch custom ops

Name reserved for the tokenspeed-trtllm-moe project.

Intelligent LLM task planner — decompose tasks, route to optimal models, enforce budgets

This package name is reserved

Framework to create LLM agents

Gemini Observatory Community TOM Broker Modules

UnOfficial Fragment (Telegram - Ton Coin) Python library

Uploads results from ragas to Tonic Validate.

GitHub Copilot SDK adapter for Azure AI Agent Server

A LangGraph-based agent for tool calling capabilities

Convert any LangChain Chat Model into a Tool Calling LLM

Open source library of large model usage tools.(开源大模型使用工具的库.)

MCP server that selects the best-suited downstream agent for a natural language query, distributed via uvx.

Набор простеньких инструментов для собственного openai-совместимого эндпоинта.

A Highly-Modularized Tool Learning Framework for LLM Based Agent

Python SDK for interacting with the Toolbox service with LangChain

Python SDK for interacting with the Toolbox service with LlamaIndex

Tools for LLM

A collection of database and RAG operation tools

A collection of database and RAG operation tools

CrewAI integration for tools402 — 100 AI agent tools via x402/USDC

LangChain integration for tools402 — 100 AI agent tools via x402/USDC

Token-Oriented Object Notation – Optimised serialization JSON for LLMs

Config-driven multi-agent orchestration kit with optional API/UI/MCP extras

CLI tool to chat with OpenAI GPT

Lightweight topic-aware document processing and retrieval

A package for integrating LLMs like GPT-3.5 and GPT-4 into topic modelling

Official implementation of TopicGPT: A Prompt-based Topic Modeling Framework (NAACL'24)

Toroidal topology primitives for LLM coherence research (v7: replication update — inference-time bias null result, prompt hardening effective)

A topological data analysis library for detecting knowledge gaps in RAG systems.

A Python package to choose the best alternative from a finite set of decision alternatives.

TYPE YOUR DESCRIPTION HERE

A Python package to choose the best alternative from a finite set of decision alternatives.

A Python package to find TOPSIS for MCDM (Multi-Criteria Decision Analysis Method)

TOPSIS implementation as a Python package

Python package for ranking features.

This is a Python Package implementing TOPSIS

MCP server exposing llm-wiki second-brain queries to AI agents

toq protocol plugin for CrewAI

toq protocol plugin for LangChain

Easy Deep Reinforcement Learning for PyTorch

GPT-2 implemented in PyTorch

CUDA Kernels for Large Language Models (LLMs), compatible with torch.compile.

LLM and PEFT export to NNEF via torch-to-nnef.

Differentiable cognitive primitives for agentic AI

Object-oriented RL agents based on torchrl.

A fast implementation of Particle Swarm Optimization using PyTorch

TinyDB storage with orjson and msgpack

Torque and Drag Calculation

Tree-of-Thought Location Agent — an inspectable, correctable memory engine that learns places through observation and correction.

Persistent memory MCP server for Claude Code, Codex CLI, Cursor and any MCP client: 46 tools — knowledge graph, temporal facts, procedural memory, episodic memory, AST ingest, pre-edit guard, auto-consolidating error capture

On-chain memory infrastructure for AI agents — built on the Internet Computer

Python uchun sayohat turlarini boshqaruvchi kutubxona

Toy GPT next-token prediction using a unigram model.

Toy GPT next-token prediction using a bigram model.

Toy GPT next-token prediction using a 2-token context window.

Toy GPT next-token prediction using a 3-token context window.

A toy python package

Toy LLM

A new package designed to streamline content management tasks within Textpattern CMS 4.9.0. It allows users to input text-based content or instructions related to their CMS, such as article drafts, fo

Comprehensive TPS monitoring and throttling library with database-driven controls

Some simple utils packaging OpenAI util.

Cross-CLI plugin marketplace installer for agent-forge

Developer toolkit for Claude Code: multi-model proxy routing, session management, policy engine, and skills architecture

An extension for TRAC D.A.P. that lets models connect to OpenAI endpoints

LangChain callback integration for TraceAgent.

TraceAgent SDK for instrumenting AI agents.

TraceAgent FastAPI backend server.

TraceAgent UI static server.

OpenTelemetry instrumentation for DSPy

OpenTelemetry instrumentation for Anthropic

OpenTelemetry instrumentation for AutoGen v0.4+ (AgentChat)

OpenTelemetry instrumentation for Bedrock

OpenTelemetry instrumentation for Cohere - embeddings, chat, and rerank

OpenTelemetry instrumentation for Crewai

OpenTelemetry instrumentation for Groq

OpenTelemetry instrumentation for Haystack

OpenTelemetry instrumentation for Langchain

OpenTelemetry instrumentation for LiteLLM

OpenTelemetry instrumentation for Llama Index

OpenTelemetry instrumentation for Mistral AI

OpenTelemetry instrumentation for Ollama - local LLM runner

OpenTelemetry instrumentation for OpenAI

OpenTelemetry instrumentation for OpenAI Agents

OpenTelemetry instrumentation for Smolagents

OpenTelemetry instrumentation for vLLM

Traceable.ai Python Agent

TraceAgent — Local-first AI agent observability SDK. Trace LangChain, LangGraph, and any Python code. Open-source alternative to LangSmith.

Real-time observability for AI agents. See every thought, tool call, and error — live.