PyPI agents

OpenTelemetry instrumentation for Claude Agent SDK

OpenTelemetry instrumentation for Pydantic AI

Agent runtime tracing and deterministic replay for LLM applications

Local-first observability for LLM applications

TraceMem — memory hooks installer for Claude Code

TRACER: Trace-Based Adaptive Cost-Efficient Routing. Turn LLM traces into parity-gated routing policies - cut 90%+ of LLM calls with formal guarantees.

Drop-in TraceRazor-instrumented Anthropic client. Zero-friction token efficiency auditing.

TraceRazor callback adapter for CrewAI - automatic token efficiency auditing

TraceRazor LangGraph/LangChain callback - token efficiency auditing

Drop-in TraceRazor-instrumented OpenAI client. Zero-friction token efficiency auditing.

TraceRazor hooks adapter for the OpenAI Agents SDK

Signed execution receipts for every LangChain model and tool call.

Placeholder package name reserved to protect the official Tracewell project.

A context tracing tool for LLM

A context traceback tool for LLM

A unified async interface to upload and download blobs to/from Azure or AWS S3, switchable via env var.

LangChain tools for the TradeOdds REST API — drop-in agent integrations for quantitative pattern analysis.

TradingAgents: Multi-Agents LLM Financial Trading Framework

Web UI for TradingAgents multi-agent trading framework

A simple tool to manage traefik in a docker swarm

Simple templating and web-source retrieval utilities for RAG.

Automatic Claude context builder for any coding project

Tragedy (Ancient Greek: τραγῳδία) is one of the three principal theatrical genres.

API client for Test Results Aggregation system

Paragraph-level compliance audit trails for RAG pipelines

A small example package

Fine-tuning LLMs for instruction using QLoRA.

TrainLoop LLM Logging SDK for data collection

TRAINS Agent - Auto-Magical DevOps for Deep Learning

Mapping trait to ontology using GPT.

Multilingual Parallel Translation Platform with Reflection-based Improvement using Local LLMs

Embed transcript files into ChromaDB and query them with RAG

A modular PyTorch framework for fine-tuning Hugging Face models.

This package makes it super simple to do exploratory data analysis and develop high-quality Panel data apps ...

An OpenAI Completions API compatible server for NLP transformers models

A library for transforming unstructured text into structured data without context/mappings using ChatGPT.

Translate Latex articles through LLM and compile them into PDF

Add your description here

LLMtranslator translates and generates text in multiple languages.

transnormerllm

Travel Agent AI Agent Directory to Host All Travel Agent related AI Agents Services, Community, Reviews and More.

An agent that books flights and hotels.

Official Implementation of "Tree of Thoughts: Deliberate Problem Solving with Large Language Models"

Tree hash-storage files

Lightweight structural RAG library — index documents as trees, query without a vector DB.

Python SDK for the Agent Orchestration API.

PostgreSQL logger for OpenAI-style LLM API interactions

A Python library for accessing Google Trends data

A Python library for accessing Google Trends data

Free, open-source Python library for Google Trends data: trending now plus keyword interest over time, related queries, and interest by region. A maintained pytrends alternative with CLI and API.

A Python SDK for AI agents built from scratch with a simple implementation of the Agent2Agent and ModelContext protocols

Using Trezor as hardware SSH/GPG agent

Classify why your agent failed. Recover intelligently.

Claude-powered CLI for Azure DevOps automation

a plugin to integrate Twisted trial with Ned Batchelder's coverage.py

block chain triangular arbitrage

An SDK to connect Gemini with the Tribulnation ecosystem.

A python package for applying TriModal Retrieval-Augmented Generation (RAG) system.

A Python SDK for Trinity Agent Monitoring API

Trip Planning Agent AI Agent Directory to Host All Trip Planning Agent related AI Agents Services, Community, Reviews and More.

Flexible and modular LLM inference for mini-batch

Run an AI agent

A new package that allows users to input a public username or handle from social media platforms, and receives a structured, humorous roast based on publicly available information. The package uses ll

Pytroll file utilities

Python LLM agent framework with multi-model support (OpenAI, Anthropic, Gemini, DeepSeek), tool calling, session management, A2A/MCP/AGUI protocols, and FastAPI server integration

Name reserved for the trtllm-kernel project.

A boilerplate utility package

Initialize TRUGS Agent in your project — a 190-word formal instruction language for LLM coding assistants

Library to systematically track and evaluate LLM based applications.

Library to systematically track and evaluate LangGraph based applications.

Library to systematically track and evaluate LLM based applications.

Library to systematically track and evaluate LLM based applications.

Library to systematically track and evaluate LLM based applications.

Library to systematically track and evaluate LLM based applications.

Library to systematically track and evaluate LLM based applications.

Library to systematically track and evaluate LLM based applications.

Library to systematically track and evaluate LLM based applications.

Trustay Agent Workflow CLI and managed agent workflow assets.

TrustChain Agent OS — Trust-native protocol layer for AI agents

Run Claude Code inside a podman container, wrapped by gVisor.

Trusted AI Agent Governance Engine

TrustGraph provides a means to run a pipeline of flexible AI processing components in a flexible means to achieve a processing pipeline.

TrustLLM

RAG Framework within Reliable input,Trusted output

RAGAS-based evaluation pipeline with trust-specific metrics for TrustRAG

LangChain integration for TrustRAG — trust-verified retrieval + LangGraph multi-hop agent with trust budget

MCP server for TrustRAG — trust-verified RAG exposed as tools for Claude Desktop, Cursor, and other MCP clients

Core functionality for TLM

A Python-based code scanning tool for AI/LLM-specific vulnerabilities

Truthlocks MAIP wrapper for Anthropic — auto-generate cryptographic receipts for every Claude API call

Truthlocks MAIP integration for AutoGen — auto-generate cryptographic receipts for every multi-agent conversation

Truthlocks MAIP wrapper for AWS Bedrock — auto-generate cryptographic receipts for every model invocation

Truthlocks MAIP integration for CrewAI — auto-generate cryptographic receipts for every crew task and agent action

Truthlocks MAIP integration for LangChain — auto-generate cryptographic receipts for every chain and agent action

Truthlocks MAIP integration for LlamaIndex — auto-generate cryptographic receipts for every query and retrieval

Truthlocks MAIP wrapper for OpenAI — auto-generate cryptographic receipts for every API call

Claim-grounded truth evaluation for LLM outputs: retrieval, per-claim verification, and explicit risk signals

CrewAI adapter for TruthStack supplement safety API. Check drug interactions, get evidence, search compounds.