Python agents

Cursor ve Claude Code'u Telveguard'a bağlayan hook'lar ve kurum hesabıyla giriş (telve)

Migrate Temporal Python workflows to Mistral Workflows (codemod + migration report)

Temporal integration for deepagents

Temporal integration for langgraph

Temporal integration for strands agents

The Tenbri Agent Decision Record for the Claude Agent SDK: every tool call a signed, provable decision.

The Tenbri Agent Decision Record for LangGraph and LangChain: every tool call a signed, chained decision.

The Tenbri Agent Decision Record for the OpenAI Agents SDK: every tool call, handoff and approval signed, chained and provable.

Placeholder that reserves the name for TenetRAG, a Python SDK for GraphRAG. Not usable yet.

TensorRT Edge-LLM model build and inference package

Population-weighted heat exposure for the areas where health data is recorded.

Grounded question answering over technical books, with citation and code verification.

Python SDK for ThailandHosting Object Storage

LiteLLM's API with Agent Router underneath: the SDK and the local gateway.

LiteLLM's API with Agent Router underneath: the SDK alone, for use with a remote gateway. pip install theagentrouter adds the local gateway.

Agent Router's aigw program, for theagentrouter's local gateway. Installed with pip install theagentrouter.

Lightweight, SDK-free, zero-dependency Python wrapper for chat completions (with streaming) and embeddings across 18 LLM providers behind one normalized surface.

LLM cost routing with correct per-request cost: output-length forecasting, cache-aware tiered pricing, and $/quality ranking.

Thunder — the human engine for AI agents: stealth browser body, human hands, TLS ghost, CAPTCHA bridge, and a stewmind thought layer.

SDK that wraps Tikuu agent handlers in FastAPI /ping, /invoke, /stream, and /ws

tina 的实验性多 Agent 场景（消息总线 + Web 调试控制台）

Async persistent LangGraph memory with exact namespaces and structured search.

Courbes de titrage acido-basique sans approximation : pH, polyacides, mélanges, dilution, équivalences, méthode des tangentes, et une base de couples.

A firmware map for your AI agent. Treasure Map draws the map; your agent finds the treasure.

Standalone llms.txt provider for Toolframe

Retrieval regression testing in CI: trec_eval-equal metrics, per-query diffs, significance tests and leakage checks.

The Tracepanel agent: keeps your app's traces and logs, finds N+1 queries and other issues, serves the local console

An AI analyst picks the trade; tested Python places it on Robinhood with hard limits and an automatic exit.

Autonomous trading agents with deterministic execution. The agents propose; the system decides.

Tripwire hard-stop and ingest callback for a customer's LiteLLM proxy

Installs webcli, which provides the llmcli command (chat AIs over your own signed-in Chrome).

Convert integers to and from Roman numerals, with validation.

Python client for the MockAgent API

Tilde adapter for CrewAI: convert invocation history to CrewAI messages and channel tools to CrewAI tools

Tilde adapter for LangChain and LangGraph: typed context to LangChain messages and channel tools

Tilde adapter for the OpenAI Agents SDK: typed history to Responses input items and channel tools to function tools

Tilde adapter for Pydantic AI: typed context to model messages, channel tools to Pydantic AI tools

Tune LangChain, LangGraph, and Google ADK RAG pipelines

Measure which parts of a Turkish RAG pipeline pay off: chunking, stemming, embedding model, fusion.

Haystack integration for TypeSafe System One decision models

Ship the errors your Python app already logs to UptimeAgent, so incidents arrive with your own error lines attached. Evidence only, never a vote on uptime. Zero dependencies.

RAG and agentic AI security auditor: prompt injection, context poisoning, data exfiltration

CrewAI adapter for VantaDB — embedded vector memory for AI agents

DSPy adapter for VantaDB — embedded vector memory for AI agents

Haystack adapter for VantaDB — embedded vector memory for AI agents

LangChain adapter for VantaDB — embedded vector memory for AI agents

LiteLLM embedding gateway + VantaDB storage — unified embedding provider with local vector search

LlamaIndex adapter for VantaDB — embedded vector memory for AI agents

Ollama local embedding API wrapper + VantaDB storage — generate embeddings via Ollama and store/search them in VantaDB

OpenAI embedding API wrapper + VantaDB storage — generate embeddings via OpenAI and store/search them in VantaDB

sllm: a high-performance LLM inference engine (placeholder; first release coming soon)

Python client for the Vedika agent harness.

Read car data through your KTuner dongle, analyze it, and write a new .kcl tune file to review and flash in KTuner. Built for AI agents.

Haystack component for Veida AI image generation, usable with no API key

SLA-aware request scheduling for LLM serving, with a mock engine, an API server and benchmark tools

Ventri Agent: a DeepSeek-first personal agent built on the Ventri kernel (placeholder, under active development).

Parallel scene generation for video explainer pipeline via Claude Agent SDK + FastMCP

Production hierarchical RAG: structure-aware Search, agentic retrieval, experience edges

Vinc for Microsoft Agent Framework: bring decisions and records from your knowledge graph into each agent run, without writing anything on its own.

Vinc for LangGraph and LangChain agents: bring decisions and records from your knowledge graph into graph nodes and model calls, and record an episode only when you choose to.

A live map of which agent in a multi-agent AI system is doing what - from its chain of thought.

Core agent orchestration, tools, and business logic for Vivexy

Run script-defined vLLM benchmarks through Docker Compose or Modal.

IQuest-Q1 models and parsers for vLLM

vLLM plugin: keeps the Flash-Next PLE table out of the vLLM process (per-machine agent with a shared cache, local file and/or central server)

A high-throughput and memory-efficient inference and serving engine for LLMs

XTU (X Transformers Unity) — a mainline-vLLM hybrid MoE plugin (CPU experts + GPU attention/long prefill). Bundles the xiaotu CPU MoE engine (AVX512-VNNI/BF16: MXFP4/FP8/INT4/BF16) so no-AMX x86 hosts (AMD EPYC) get usable CPU MoE backends through FusedMoEFactory.

Zero-install CLI for any LLM agent to join a voicehook.ai voice call as a 2nd participant

VoiceLayer channels for agent frameworks: the channel MCP tools for the Claude Agent SDK, OpenAI Agents and LangChain/LangGraph, and direct mode.

Volcengine secagent SDK for Python

Volcengine storageebs SDK for Python

VT-AIAgent — system-automation agent exposed as an MCP server for opencode/claude/pi

Name reserved by VyomGrid. The real package is installed from https://github.com/Mikhil1990/sdlc-agent-loop-marketplace/releases

AgenticGuard SDK for Python: tamper-evident records of what AI agents do. First release coming soon.

WebAgent Protocol: an MCP extension that lets AI agents discover, verify and safely use tools published by any website.

Haystack component for Webz.io News Search

Whiteout guardrail for the LiteLLM Proxy — govern every app behind the gateway

Attaches WhiteRoom session attestation to a boto3 bedrock-runtime client

AST-aware operation registry and multi-provider task queue

Mesh Acts and compatible Willman mesh infrastructure

A live terminal panel for llama.cpp's llama-server on Windows: GPU and shared memory, RAM, requests

llama.cpp backend core for the Windows ML Runtime

PyWinRT projection of the Windows.AI.Agents.Mcp namespace

终端里的多 Agent 助手，可选择市面上的 OpenAI 兼容模型

Eval harness for Claude Code agents: golden tasks, rule checks, LLM-judge rubrics, traces, cost/latency, regression gate.

Python SDK for building applications on top of the WormGPT API.

A coding agent for the terminal

A local-first, resumable workflow CLI for people and AI agents.

Read-only x.com (Twitter) API client for LLM agents: library, CLI, and stdio MCP server

xfA (x for Agents): one identity for all your agents. Set up at https://xfa.sh

In-process Python SDK for the Xiaoyu workspace execution engine

Opt-in XMemo context and capture for Microsoft Agent Framework

Enterprise Multi-Agent Runtime, MTPO Lock-Free Concurrency & AST Security Governance Framework

Xsite Agentic_SayarGyi terminal client

Files on local disk, in memory or in object stores, behind one async interface.

A ModelProvider for OpenAI-compatible chat and embedding endpoints, proved against the shipped conformance suite