Open Source Capability Building Projects

LLM Application Framework Public

langchain

LLM application framework for checking model, prompt, tool, retrieval, and chain integration boundaries.

LLM appsRAGTool calling

Software Development & Delivery Public

codex

Lightweight coding agent that runs in your terminal

Software Development & Delivery Public

OpenHands

🙌 OpenHands: AI-Driven Development

Software Development & Delivery Public

Ansible is a radically simple IT automation platform that makes your applications and systems easier to deploy and maintain. Automate everything from code deployment to network configuration to cloud management, in a language that approaches plain English, using SSH, with no agents to install on remote systems. https://docs.ansible.com.

Workflow Automation Public

autogen

A programming framework for agentic AI

Software Development & Delivery Public

OpenSpec

Spec-driven development (SDD) for AI coding assistants.

Security Review & Permission Governance Public

Docker-OSX

Run macOS VM in a Docker! Run near native OSX-KVM in Docker! X11 Forwarding! CI/CD for OS X Security Research! Docker mac Containers.

Software Development & Delivery Public

prettier

Prettier is an opinionated code formatter.

Customer and Team Operations Public

twenty

Customer and team operations project for checking CRM/low-code data models, permissions, workflows, and rollback.

CRMLow-codeTeam workflows

Software Development & Delivery Public

ray

Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

Software Development & Delivery Public

harness

Harness Open Source is an end-to-end developer platform with Source Control Management, CI/CD Pipelines, Hosted Developer Environments, and Artifact Registries.

Software Development & Delivery Public

trivy

Find vulnerabilities, misconfigurations, secrets, SBOM in containers, Kubernetes, code repositories, clouds and more

Software Development & Delivery Public

marker

Convert PDF to markdown + JSON quickly with high accuracy

Software Development & Delivery Public

dspy

DSPy: The framework for programming—not prompting—language models

Software Development & Delivery Public

posthog

🦔 PostHog is an all-in-one developer platform for building successful products. We offer product analytics, web analytics, session replay, error tracking, feature flags, experimentation, surveys, data warehouse, a CDP, and an AI product assistant to help debug your code, ship features faster, and keep all your usage and customer data in one stack.

LLM Application Framework Public

langgraph

LLM application framework for checking model, prompt, tool, retrieval, and chain integration boundaries.

LLM appsRAGTool calling

Vector Retrieval and RAG Public

sim

Vector retrieval project for checking embedding storage, query semantics, RAG integration, data boundaries, and rollback.

Vector databaseRAGEmbeddings

Vector Retrieval and RAG Public

chroma

Vector retrieval project for checking embedding storage, query semantics, RAG integration, data boundaries, and rollback.

Vector databaseRAGEmbeddings

Research & Knowledge Management Public

gitleaks

Find secrets with Gitleaks 🔑

Vector Retrieval and RAG Public

supermemory

Vector retrieval project for checking embedding storage, query semantics, RAG integration, data boundaries, and rollback.

Vector databaseRAGEmbeddings

Developer Workflow Public

vibe-kanban

Developer workflow project for checking task state, code/agent collaboration, permissions, and delivery boundaries.

Developer workflowTask boardAgent collaboration

MCP Tool Integration Public

agentscope

MCP tool integration project for safely connecting external tools, services, or data sources to an AI host.

MCPTool callingHost configuration

Software Development & Delivery Public

trufflehog

Find, verify, and analyze leaked credentials

Software Development & Delivery Public

shields

Concise, consistent, and legible badges in SVG and raster format

MCP Tool Integration Public

crush

MCP tool integration project for safely connecting external tools, services, or data sources to an AI host.

MCPTool callingHost configuration

Personal Workspace Public

letta

Platform for stateful agents: AI with advanced memory that can learn and self-improve over time.

Data and AI Pipeline Public

prefect

Data and AI pipeline project for checking inputs, outputs, state, latency, recovery, and deployment boundaries.

Data pipelineAI workflowState management

MCP Tool Integration Public

marimo

MCP tool integration project for safely connecting external tools, services, or data sources to an AI host.

MCPTool callingHost configuration

Tool Connections & Integrations Public

MaxKB

MaxKB is a Doramagic preview pack compiled from public project evidence and validation signals.

Software Development & Delivery Public

peft

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

MCP Tool Integration Public

adk-python

MCP tool integration project for safely connecting external tools, services, or data sources to an AI host.

MCPTool callingHost configuration

MCP Tool Integration Public

owl

MCP tool integration project for safely connecting external tools, services, or data sources to an AI host.

MCPTool callingHost configuration

Agent SDK and Runtime Public

pydantic-ai

Agent SDK project for checking tool calls, state, handoffs, traces, evaluation, and permission boundaries.

Agent SDKTool callsHandoffs

Software Development & Delivery Public

olmocr

Toolkit for linearizing PDFs for LLM datasets/training

Observability and Evaluation Public

deepeval

Observability and evaluation project for turning logs, quality metrics, drift, or experiment results into reviewable signals.

ObservabilityEvaluationQuality metrics

Data and AI Pipeline Public

dagster

Data and AI pipeline project for checking inputs, outputs, state, latency, recovery, and deployment boundaries.

Data pipelineAI workflowState management

Software Development & Delivery Public

tvm

Open Machine Learning Compiler Framework

Software Development & Delivery Public

instructor

structured outputs for llms

Tool Connections & Integrations Public

reaction

Project has been discontinued ////// Mailchimp Open Commerce is an API-first, headless commerce platform built using Node.js, React, GraphQL. Deployed via Docker and Kubernetes.

Vector Retrieval and RAG Public

turbovec

Vector retrieval project for checking embedding storage, query semantics, RAG integration, data boundaries, and rollback.

Vector databaseRAGEmbeddings

Software Development & Delivery Public

botkit

Botkit is an open source developer tool for building chat bots, apps and custom integrations for major messaging platforms.

Data Analysis & Investment Research Public

kedro

Kedro is a toolbox for production-ready data science. It uses software engineering best practices to help you create data engineering and data science pipelines that are reproducible, maintainable, and modular.

Research & Knowledge Management Public

openvino

OpenVINO™ is an open source toolkit for optimizing and deploying AI inference

Software Development & Delivery Public

metaflow

Build, Manage and Deploy AI/ML Systems

Software Development & Delivery Public

BentoML

The easiest way to serve AI apps and models - Build Model Inference APIs, Job queues, LLM apps, Multi-model pipelines, and more!

Security Review & Permission Governance Public

garak

the LLM vulnerability scanner

Security Review & Permission Governance Public

bandit

Bandit is a tool designed to find common security issues in Python code.

Vector Retrieval and RAG Public

deep-searcher

Vector retrieval project for checking embedding storage, query semantics, RAG integration, data boundaries, and rollback.

Vector databaseRAGEmbeddings

MCP Tool Integration Public

Upsonic

MCP tool integration project for safely connecting external tools, services, or data sources to an AI host.

MCPTool callingHost configuration

Observability and Evaluation Public

evidently

Observability and evaluation project for turning logs, quality metrics, drift, or experiment results into reviewable signals.

ObservabilityEvaluationQuality metrics

Tool Connections & Integrations Public

steel-browser

🔥 Open Source Browser API for AI Agents & Apps. Steel Browser is a batteries-included browser sandbox that lets you automate the web without worrying about infrastructure.

Research & Knowledge Management Public

feast

The Open Source Feature Store for AI/ML

MCP Tool Integration Public

OpenSpace

MCP tool integration project for safely connecting external tools, services, or data sources to an AI host.

MCPTool callingHost configuration

Data and AI Pipeline Public

marvin

Data and AI pipeline project for checking inputs, outputs, state, latency, recovery, and deployment boundaries.

Data pipelineAI workflowState management

Software Development & Delivery Public

trafilatura

Python & Command-line tool to gather text and metadata on the Web: Crawling, scraping, extraction, output as CSV, JSON, HTML, MD, TXT, XML

MCP Tool Integration Public

genkit

MCP tool integration project for safely connecting external tools, services, or data sources to an AI host.

MCPTool callingHost configuration

Research & Knowledge Management Public

minisearch

Tiny and powerful JavaScript full-text search engine for browser and Node

Frontend Agents and Generative UI Public

harness-sdk

Frontend agent and generative UI project for checking React/Angular integration, app actions, UI state, and UX boundaries.

Generative UIFrontend agentsReact

Software Development & Delivery Public

potpie

Spec-driven development for large codebases

Software Development & Delivery Public

zenml

ZenML 🙏: One AI Platform from Pipelines to Agents. https://zenml.io.

Research & Knowledge Management Public

TaskingAI

The open source platform for AI-native application development.

Vector Retrieval and RAG Public

superduper

Vector retrieval project for checking embedding storage, query semantics, RAG integration, data boundaries, and rollback.

Vector databaseRAGEmbeddings

Software Development & Delivery Public

agents-cli

The CLI and skills that turn any coding assistant into an expert at creating, evaluating, and deploying AI agents on Google Cloud.

Vector Retrieval and RAG Public

infinity

Vector retrieval project for checking embedding storage, query semantics, RAG integration, data boundaries, and rollback.

Vector databaseRAGEmbeddings

Customer Communication & Team Operations Public

detect-secrets

An enterprise friendly way of detecting and preventing secrets in code.

MCP Tool Integration Public

gptme

MCP tool integration project for safely connecting external tools, services, or data sources to an AI host.

MCPTool callingHost configuration

Research & Knowledge Management Public

agenta

The open-source LLMOps platform: prompt playground, prompt management, LLM evaluation, and LLM observability all in one place.

Software Development & Delivery Public

AdalFlow

AdalFlow: The library to build & auto-optimize LLM applications.

Tool Connections & Integrations Public

yacy_search_server

Distributed Peer-to-Peer Web Search Engine and Intranet Search Appliance

MCP Tool Integration Public

SimpleMem

MCP tool integration project for safely connecting external tools, services, or data sources to an AI host.

MCPTool callingHost configuration

Data Analysis & Investment Research Public

sqlmesh

Scalable and efficient data transformation framework - backwards compatible with dbt.

Personal Workspace Public

ReMe

ReMe: Memory Management Kit for Agents - Remember Me, Refine Me.

Tool Connections & Integrations Public

fastembed

Fast, Accurate, Lightweight Python library to make State of the Art Embedding

Software Development & Delivery Public

OSWorld

[NeurIPS 2024] OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments

Research & Knowledge Management Public

Jets.js

Native CSS search engine

Data Analysis & Investment Research Public

hamilton

Apache Hamilton helps data scientists and engineers define testable, modular, self-documenting dataflows, that encode lineage/tracing and metadata. Runs and scales everywhere python does.

Software Development & Delivery Public

code-interpreter

Python & JS/TS SDK for running AI-generated code/code interpreting in your AI app

Data Analysis & Investment Research Public

portaljs

🌀 AI-native framework for building data portals. Scaffold a full portal from a brief and load datasets in minutes with agentic skills — any backend (CKAN, GitHub, Frictionless).

Vector Retrieval and RAG Public

LLMStack

Vector retrieval project for checking embedding storage, query semantics, RAG integration, data boundaries, and rollback.

Vector databaseRAGEmbeddings

Self-hosted AI Workspace Public

deep-research-web-ui

Self-hosted LLM web UI covering Docker deployment, auth, model backends, OAI/Ollama endpoints, and reverse proxy checks.

Self-hosted LLMDocker deploymentModel backends

Vector Retrieval and RAG Public

kernel-memory

Vector retrieval project for checking embedding storage, query semantics, RAG integration, data boundaries, and rollback.

Vector databaseRAGEmbeddings

Vector Retrieval and RAG Public

yt-fts

Vector retrieval project for checking embedding storage, query semantics, RAG integration, data boundaries, and rollback.

Vector databaseRAGEmbeddings

Vector Retrieval and RAG Public

memanto

Vector retrieval project for checking embedding storage, query semantics, RAG integration, data boundaries, and rollback.

Vector databaseRAGEmbeddings

MCP Tool Integration Public

ktx

MCP tool integration project for safely connecting external tools, services, or data sources to an AI host.

MCPTool callingHost configuration

MCP Tool Integration Public

chunkhound

MCP tool integration project for safely connecting external tools, services, or data sources to an AI host.

MCPTool callingHost configuration

Software Development & Delivery Public

spacy-layout

📚 Process PDFs, Word documents and more with spaCy

Software Development & Delivery Public

pipelex

Declarative language for composable Al workflows. Devtool for agents and mere humans.

Software Development & Delivery Public

kernels

Build compute kernels and load them from the Hub.

MCP Tool Integration Public

pipenet

MCP tool integration project for safely connecting external tools, services, or data sources to an AI host.

MCPTool callingHost configuration

Software Development & Delivery Public

djblets

A collection of useful extensions for Django.

Software Development & Delivery Public

vite-plugin-top-level-await

Transform code to support top-level await in normal browsers for Vite.

Vector Retrieval and RAG Public

agent-memory-server

Vector retrieval project for checking embedding storage, query semantics, RAG integration, data boundaries, and rollback.

Vector databaseRAGEmbeddings

MCP Tool Integration Public

OpenHands-CLI

MCP tool integration project for safely connecting external tools, services, or data sources to an AI host.

MCPTool callingHost configuration

Software Development & Delivery Public

ReviewBot

A tool for running automated static analysis on code posted to a Review Board instance.

Vector Retrieval and RAG Public

ToM-SWE

Vector retrieval project for checking embedding storage, query semantics, RAG integration, data boundaries, and rollback.

Vector databaseRAGEmbeddings

Software Development & Delivery Public

creact

CReact is how you write your workflows using JSX, build durable apps that you can sync with external state, build jobs, agents, infrastructure, anything you can declare you can build!

MCP Tool Integration Public

instar

MCP tool integration project for safely connecting external tools, services, or data sources to an AI host.

MCPTool callingHost configuration

Software Development & Delivery Public

kgb

Python function spy support for unit tests

Security Review & Permission Governance Public

agentlock

An adversarially benchmarked reference implementation for pre-action agent authorization. Framework-agnostic tool permissions, identity verification, scoped access control, and audit logging for any AI agent.

MCP Tool Integration Public

termyte

MCP tool integration project for safely connecting external tools, services, or data sources to an AI host.

MCPTool callingHost configuration

Software Development & Delivery Public

python-registries

Create registries managing collections of classes or objects, for more extensible and maintainable codebases.

Vector Retrieval and RAG Public

Vex

Vector retrieval project for checking embedding storage, query semantics, RAG integration, data boundaries, and rollback.

Vector databaseRAGEmbeddings

MCP Tool Integration Public

Moryn

MCP tool integration project for safely connecting external tools, services, or data sources to an AI host.

MCPTool callingHost configuration

Customer and Team Operations Public

oto-cli

Customer and team operations project for checking CRM/low-code data models, permissions, workflows, and rollback.

CRMLow-codeTeam workflows

MCP Tool Integration Public

forgekit

MCP tool integration project for safely connecting external tools, services, or data sources to an AI host.

MCPTool callingHost configuration

MCP Tool Integration Public

membook

MCP tool integration project for safely connecting external tools, services, or data sources to an AI host.

MCPTool callingHost configuration

Tool Connections & Integrations Public

grok-faf-voice

Python SDK that gives xAI Grok Voice agents persistent memory across sessions, devices, and models. LiveKit-enabled. MIT licensed.

MCP Tool Integration Public

oh-no-my-claudecode

MCP tool integration project for safely connecting external tools, services, or data sources to an AI host.

MCPTool callingHost configuration

Software Development & Delivery Public

omniconductor

One workflow framework, every coding agent. Install your AI-coding discipline into Claude Code, Cursor, GitHub Copilot, Gemini CLI, Codex, and Windsurf from one tool-agnostic core. Apache 2.0.

Software Development & Delivery Public

python-typelets

Type hints and utility objects for Python and Django projects.

Personal Workspace Public

skul

Manage project-scoped personal AI configuration bundles (skills, commands, agents) for AI coding tools while supporting both stealth (git-excluded) and tracked installation, with full support for Git worktrees.

Security Review & Permission Governance Public

vorim-agent-audit

Free AI agent code hygiene checker. Scans for hardcoded LLM keys, shared credentials, and long-lived permissions in TypeScript, JavaScript, and Python projects. By Vorim AI.

MCP Tool Integration Public

aegisdb

MCP tool integration project for safely connecting external tools, services, or data sources to an AI host.

MCPTool callingHost configuration

MCP Tool Integration Public

agent-device

MCP tool integration project for safely connecting external tools, services, or data sources to an AI host.

MCPTool callingHost configuration

MCP Tool Integration Public

anamnesis

MCP tool integration project for safely connecting external tools, services, or data sources to an AI host.

MCPTool callingHost configuration

Security Review & Permission Governance Public

arcjet-js

Arcjet runtime security SDK for Next.js — bot protection, rate limiting, prompt injection detection, PII blocking, and WAF

Software Development & Delivery Public

boffin

**Boffin (npm: `boffinit`) is a staff-engineer control layer for AI coding

Software Development & Delivery Public

cactus-hybrid

Cactus Hybrid

Software Development & Delivery Public

cli

The official CLI for Lark/Feishu open platform

MCP Tool Integration Public

copilot-cli

MCP tool integration project for safely connecting external tools, services, or data sources to an AI host.

MCPTool callingHost configuration

Security Review & Permission Governance Public

csec-node-agent

New Relic Security Agent for Node.js

Security Review & Permission Governance Public

deepsec

`deepsec` an agent-powered vulnerability scanner that you can run in your own infrastructure, optimized to perform on-demand review of all code in existing

MCP Tool Integration Public

firebase-tools

MCP tool integration project for safely connecting external tools, services, or data sources to an AI host.

MCPTool callingHost configuration

Software Development & Delivery Public

graphrefly-py

Reactive harness layer for agent workflows. Describe automations in plain language, trace every decision, enforce policies, persist checkpoints. Python. Zero dependencies.

Software Development & Delivery Public

kilocode

The AI coding agent built for the terminal. Generate code from natural language, automate tasks, and run terminal commands -- powered by 500+ AI models.

Research & Knowledge Management Public

loopgain

**An open-source cost controller for AI agent loops.**

Data Analysis & Investment Research Public

mantine-datatable

Mantine DataTable

Software Development & Delivery Public

nimic

Nimic is a pure Python module that facilitates writing AOT compilable code with a subset of Python (domain specific language), aiming to get C-level performance without leaving Python. Based on ctypes built-in module, it

Software Development & Delivery Public

node-newrelic

New Relic agent

Software Development & Delivery Public

officecli

> **OfficeCLI is the world's first and the best Office suite designed for AI agents.**

LLM Application Framework Public

openwiki

LLM application framework for checking model, prompt, tool, retrieval, and chain integration boundaries.

LLM appsRAGTool calling

Research & Knowledge Management Public

Customer Communication & Team Operations Public

telecom-mas-agent

A conversational AI-driven telecom multi-agent system for managing call balances, push notifications, marketing, targeting, and sales.