Python agents

Project: Machine Learning for Trading and Portfolio Management (ENSAE)

Drop-in prompt injection defense for LLM apps and AI agents — detect, sanitize, block, and audit injection attacks in real time. Includes multi-turn session scanning, allow-lists, rate-abuse detection, multi-layer scanner, FastAPI and Flask middleware.

Deterministic Unicode-aware input hardening for LLM applications.

A package for sanitizing and securing user inputs to LLMs

A comprehensive toolkit for LLM evaluation, prompt engineering, fine-tuning, and inference optimization

A Python Library to download all the required LLM Python packages for building an LLM-based chatbot

A high-performance instrumentation framework for capturing, streaming, and analyzing internal activations of large language models

LLM Integrity → This package is now `aiir`. Install: pip install aiir

Async multi-provider LLM client with typed tool calling, lazy output parsing, and Azure/Databricks/OpenRouter/LiteLLM/DeepSeek/local backends

A proxy server to intercept and store LLM API calls for fine-tuning dataset collection

Intercept and analyze LLM traffic from AI coding tools

A flexible interface for working with various LLM providers

LLM plugin for interpolating between embeddings

Candidate CLI for submitting LLM interview history.

A Python library for managing multi-agent model invocation with automatic failover strategies

A lightweight Model I/O normalization layer for OpenAI-compatible LLM calls.

A jailbreak package which integration some open manners

LLM plugin for Jina AI

Access Jina AI embeddings via their API

LLM plugin for pulling content from Jina Reader API

Fuzzy join pandas DataFrames using LLM scoring and embedding retrieval — record linkage, entity resolution, approximate join

Write and execute jq programs with the help of LLM

A JSON library wrapper that gracefully handles markdown-wrapped JSON from LLMs.

使用 LLM 修正 json 文件

A simple utility to fix malformed JSON from LLM outputs

Production-safe JSON repair and schema validation for LLM outputs

Robust JSON parsing for LLM outputs with automatic repair and field extraction

A unified interface for streaming structured JSON from OpenAI, Anthropic, and Google Gemini.

Fast, minimal JSON repair implemented in Rust (PyO3), focusing on truncation and trailing comma fixes.

A Python package for converting unstructured text into JSONL format using LLMs.

llm's judge each other

Run a IPython interpreter in the LLM virtual environment

A multi-model LLM evaluation framework with consensus-based aggregation for RAG, summarization, and agentic AI workflows

Confidence-driven escalation middleware for classifier edge cases

CLI knowledge base manager for markdown wikis, designed for both humans and LLM agents

One tiny model, every LLM API. Drop-in test server for OpenAI, Anthropic, Bedrock, and Vertex.

Framework for collecting and managing LLM context

Free-tier LLM API key pool with rotation, cooldown, and LangChain drop-in

A pythonic way to call llms & implement llm algorithms.

A unified toolkit for working with multiple LLM providers

Tools to extract, visualize, and quantify latent knowledge in large language models

A plugin for LLM that adds tools to interact with a Go knowledge graph.

A minimal, notebook-first framework for running reproducible LLM experiments and comparing multiple models over JSONL/CSV datasets.

LLM Labeling UI is an open source project for large language model data labeling

LLM access to LAMBDA's API

Run prompts against LLMs hosted by https://lambdalabs.com/

An LLM tool plugin for using Latchkey to make authenticated HTTP API requests.

Personal LLM deployments made simple.

Load and dispatch individual transformer layers from HuggingFace model checkpoints

Stream transformer blocks layer-by-layer from disk to GPU with a pipelined prefetch queue (disk → CPU RAM → pinned RAM → GPU).

LLM Development Framework - Spec-driven development for AI-assisted engineering

Cost ceiling, audit log, and kill switch for LLM agents.

Production-ready LLM client with audit trail, deterministic caching, and provenance tracking

llm-lens is a Python package for CV as NLP, where you can run very descriptive image modules on images, and then pass those descriptions to a Large Language Model (LLM) to reason about those images.

Automatic observability for LLM API calls

Local web UI for browsing and managing LLM CLI conversation history (currently: Claude Code).

A thread-safe and async rate limiter for Gemini and OpenAI models.

LLM-oriented CLI linter — catch quality drift before it hardens (Rust binary).

A Python package to list and monitor available LLM models from various providers

LLM plugin for LiteLLM proxy server

LLM plugin for LiteLLM OpenAI-compatible proxies

Use LLM to chat in your terminal and receive async responses

LLM plugin for running models using llama.cpp

Interact with llama-server models

LLM plugin providing access to llama.cpp server models

Access llamafile localhost models via LLM

A middleware layer for managing, budgeting, and optimizing LLM context windows.

LLM plugin for models served by LMStudio (local LLM studio HTTP API)

Agentic interface to local LLMs with tree-based context management.

Structured output contract testing for LLM systems

AI-powered log analyzer for CI environments using LLMs

Lightweight LLM call logger for OpenAI/Anthropic

Set logging.DEBUG while running LLM

Privacy-first LLM chat log parser for deterministic local analysis and export

Feedback on LLM logs (prompts & response)

Give your AI agents persistent, searchable long-term memory with pluggable storage backends

A utility package for querying language models with pattern matching and retry logic

An LLM CLI plugin to loop tool calls with turn limits and custom system prompts.

Lucid Memory - Modular reasoning graph for LLMs

multi-agent development

LLM Magics for Ipython created by kmkolasinski

the small distributed language model toolkit. fine-tune state-of-the-art LLMs anywhere, rapidly.

Flash-built LLM workflows

MapReduce-inspired framework for extending context windows in large language models

Turn Python functions into typed LLM calls using docstrings as prompts

Convert PDFs, images to high-quality Markdown using Vision LLMs.

Plugin for LLM adding a Markov chain generating model

Mask sensitive data in documents using a local OpenAI-compatible LLM

An llm plugin that provides a matched-responses model for testing - returns configurable responses based on input patterns

Retrieval-backed LLMs for math education

llm_matrix

llm implementation of MCP for clients and servers.

LLM plugin for Model Context Protocol (MCP) integration

A minimal MCP service for testing LLM understanding and invocation of MCP tools

An experimental project using Monte Carlo Tree Search (MCTS) to refine LLM responses for better accuracy and decision-making.

llm-mddocgen - Large Language Model Markdown Document Generator

Guardrails for LLM-generated medical and health content

lllm-mem is a lightweight Python CLI tool designed to calculate the GPU VRAM requirements for models on Hugging Face