Open Source Libraries
A software library is a collection of reusable code that applications can call to handle common tasks or add specific capabilities. Libraries help developers avoid rebuilding established functionality, from formatting data and generating documents to managing network connections and parallel work. They can simplify complex operations, provide consistent interfaces, and make it easier to integrate capabilities into existing software.
Open source libraries cover areas such as user interfaces, APIs, data processing, networking, and language-specific utilities. When choosing one, consider its license, maturity, maintenance activity, documentation, dependencies, supported environments, and fit with your application’s architecture. Check compatibility and integration requirements, especially for security-sensitive or foundational components. Libraries are useful to individual developers and teams building, extending, or maintaining software across a wide range of platforms.
309 repositories · updated October 4, 2026
pydantic-ai-harness: Add Capabilities for Long-Running AI Agents
A Python capability library that extends Pydantic AI agents with tools and support for coding, research, memory, delegation, and context management. This repository is no longer updated; development continues in the Pydantic AI repository.
tooltrim: Compress LLM Agent Tool Outputs
tooltrim reduces oversized tool results before they enter an LLM agent’s context, using content-aware, optionally query-aware compression. It is for developers building tool-using agents who want to reduce context use while retaining access to the original output.
OpenWorkProof: Verify and Accept AI Agent Work
OpenWorkProof is an open protocol for authorizing AI agent tasks and recording verifiable execution evidence. It helps teams independently review whether work stayed within scope, then keep verification separate from human acceptance.
intent-plane: Gate Agent Actions With Auditable Authorization
intent-plane is a Go authorization gate for agent actions that can have irreversible effects. It checks declared intents against signed policy and records decisions for independent verification, with a fail-closed posture when evaluation is uncertain.
mdx-a2ui: Convert MDX to A2UI JSON
mdx-a2ui converts prose and approved components in MDX into A2UI JSON without evaluating the source. It is an experimental option for agents or tools that author MDX but need structured output for A2UI renderers.
agenticschema: Turn Structured Web Data Into Agent Tools
AgenticSchema converts Schema.org data already present in web pages into tools for AI agents. It supports browser WebMCP registration and a Node MCP server, without requiring a new backend or page API.
agent.cpp: Build Local AI Agents in C++
agent.cpp is a C++ library for building agents that run small language models locally through llama.cpp. It provides an agent loop, tools, callbacks, and support for GGUF models, grammar constraints, and LoRA adapters.
flint-chart: Create Polished Charts from Compact Specs
Flint turns semantic, human-editable chart specifications into polished visualizations for several charting backends. It is aimed at developers and AI-agent builders who want consistent chart creation without manually configuring every layout detail.
adk-rust: Build AI Agents with Rust
ADK-Rust is a modular framework for building and deploying asynchronous AI agents in Rust. It supports multiple model providers, tools, workflows, memory, and real-time voice, with composable crates for projects ranging from prototypes to production services.
xlrd: Read Data from Legacy Excel Files
xlrd is a Python library for reading cell data and formatting from legacy Excel .xls files. It suits scripts and applications that need to inspect older spreadsheets, but it does not read newer Excel formats such as .xlsx.
pdfminer.six: Extract and Analyze Content from PDFs
pdfminer.six is a Python library and command-line tool for extracting and analyzing content from PDF files. Use it when you need text, layout details, images, or document structure from PDFs in a Python workflow.
mistune: Parse Markdown in Python
Mistune is a Python library for converting Markdown to HTML, with configurable renderers and plugins. It suits applications that need Markdown processing in Python and want to extend parsing or output behavior.