Python agents

Lightweight structured tracing for LLM applications

LLMTracer: A tool to trace the execution of a program that uses LLMs and visualize the results.

Auto-track LLM cost, latency, and usage. Two lines of code, every provider.

End-to-end observability with built-in security guardrails.

A tool to view LLM call traces from JSONL log files.

Lightweight LLM observability. SQLite-based tracing with zero infrastructure.

Python bindings for LLMTrace — security-aware LLM observability

A concise description of your package.

A Python library for language detection and translation using langchain ChatModels

Text translator using OpenAI-like API.

CLI tool for preparing project data for LLM context

A package for LLM tricks

llmtune

Easy-to-use LLM fine-tuning framework

A lightweight, model-agnostic context engine for LLMs. Feed your model tasty context.

LLM URI Parsing.

Eval-Scope: Lightweight LLMs Evaluation Framework

A few utility classes for working with LLMs

LLM inference for power users.

Automatically find cheaper LLM alternatives while maintaining performance

Automatically find cheaper LLM alternatives while maintaining performance

command line tool to interact with LLM with vision

Oncoshot LLM validation framework

Security testing toolkit for LLM prompt injection vulnerabilities

Record and replay LLM API responses for fast, free, deterministic tests

LLM Hallucination & Drift Detection — Verify LLM outputs for accuracy, consistency, and reliability

Visualize how LLMs tokenize text

Command Line LLM with client-side tools support.

LLM vs. LLM: Simulates a rap battle or debate between two Large Language Models (LLMs)

Explore the answer-space for any prompt and any MLX-supported model.

An enterprise-grade LLM-based development framework, tools, and fine-tuned models

Track, tag, and report LLM API costs by feature, user, and model.

Python wrapper for the LLM Werewolf Rust binary.

Client library for LLM Whisperer

LLM-powered personal knowledge base — raw data goes in, an LLM compiles it into a structured, interlinked wiki

Standalone CLI for llmwiki — entity-based knowledge wiki compiled from any directory of text files.

Knowledge + Chat + Research Assistant - LLM-maintained knowledge bases with chat & general research capabilities

Lightweight multi-provider LLM client for Python

Lightweight Python SDK for the LLMWise multi-model API (chat, compare, blend, judge, failover).

Effortlessly harness the power of LLMs on Excel and DataFrames—seamless, smart, and efficient!

A lightweight Python toolkit for LLM text and image workflows with Ollama.

CLI for Automated article writing (Powered by GPT-3)

LLMX: A library for LLM Text Generation

Added azure GPT to the original foundation

XML parsing for LLM outputs

YAML-based LLM configuration and execution

llmz

Lightweight, extensible LLM toolkit: chat, embeddings, vector stores (Chroma, Milvus Lite).

Local-first AI agent orchestrator — manages llama.cpp, local models, and cloud APIs

lmcache_vllm: LMCache's wrapper for vllm

Thin proxy server for Claude Code and Laminar tracing

Add your description here

LM Studio-powered llms.txt generator based on DSPy tutorials.

Generate and update agent config files from LM Studio models for VS Code Copilot, OpenCode, Pi, and Codex.

Various llm agents (agent_chat, agent_tr, agent_ref, agent_imp, agent_comb) for translation

Anthropic provider for lmux

AWS Bedrock provider for lmux

Groq provider for lmux

OpenAI provider for lmux

A buyer-side HTTP 402 runtime and agent-commerce surface inspector for x402, L402, MPP, and open-web paid actions.

Storage → object.

Standalone agentic framework for local LLMs via Ollama — reliable tool calling, session persistence, and loop guards

Real-time AI agent cost monitoring and budget alerting for local development

Maturity-aware harness manager for local AI coding agents (Claude Code, Codex CLI, Copilot CLI). Audit, init, and refresh AGENTS.md / GROUNDING.md / CI on GitHub Actions / sandbox at the right S0–S3 stage; ships an installable skill.

Minimal experimental framework for building agents with local LLM deployments. Zero bloat, maximum simplicity.

LAO — Pilot Mode plus planner→coder→verifier→reviewer orchestration over LM Studio / OpenAI-compatible APIs: structured tools, permissions, skills, hierarchical memory, optional MCP, SQLite state, and optional per-plan Git.

RAG from documents in a local directory

Random request headers for local versions of browsers

A flask server for a chrome extension that querys llm models

Interface between LLMs and your data.

Local-LLM is a llama.cpp server in Docker with OpenAI Style Endpoints.

Find which local LLMs can run on your system

Converse with GPT4 LLM locally

Sentence embeddings from any local causal LLM, no fine-tuning.

Fine-tune an LLM with Unsloth

A tool for generating function arguments and choosing what function to call with local LLMs

OpenAI-like interface for local LLMs

Local-first LLM wrapper (import local_llm_wrapper) with pluggable transports (Ollama, Apple, optional Claude Code CLI) and a stable text-in text-out API.

A lightweight proxy server that converts Anthropic Messages API to OpenAI API

Create and run a local LLM with RAG

100% local RAG for Obsidian, Zotero, and Claude Code — LightRAG + Ollama + MCP

fake_useragent use local data

A familiar API from the Web, adapted to storing data locally with Python.

A familiar API from the Web, adapted to storing data locally with Python.

opengpt is a open implementation of GPT agents by openai.

A production-grade, local-first AI CLI

Local Chat Assistant powered by Ollama

Private AutoGPT Robot - Your private task assistant with GPT!

An api to query local language models using different backends

Python client library for the OpenAI API

Chat with your documents locally.

Claude (Anthropic) API emulator – LocalStack extension

LocalStack Extension: OpenAI

A Flask extension for local storage

Detect colors in images - 20 x faster than Numpy / 430 x faster than PIL

Enterprise-grade AI security SDK with prompt injection detection for Python

Load-aware scheduling layer for multi-agent systems

Local Collaborative LLMs -- Frontier AI on a Student Budget