Curated open source, analyzed
Find open source projects worth using
Hand-picked GitHub repositories with a clear analysis of what they do, who they are for and how they compare.
1,672 repositories ·170 topics· updated daily
Featured repository
openharness: Manage Coding Agents Across Machines
A desktop command center for running coding agents in tmux across local and remote machines. OpenHarness combines terminal sessions, encrypted connections, worktrees and optional craft-specific harnesses for work beyond software.
Explore by topic
Jump into the most common areas across analyzed repositories.
Recently added
The newest projects added to the catalog.
openharness: Manage Coding Agents Across Machines
A desktop command center for running coding agents in tmux across local and remote machines. OpenHarness combines terminal sessions, encrypted connections, worktrees and optional craft-specific harnesses for work beyond software.
tramAI: Govern AI Workflows on the JVM
TramAI is a Kotlin-first JVM runtime for typed AI workflows with configurable policy, provider routing, tool controls, approvals, and execution evidence. It suits teams that need governance around model use, not just a way to call an LLM.
5dive-a2a: Send Signed Messages Between AI Agents
A 5dive plugin for direct, signed messaging between agents on separate servers. It verifies contacts, queues messages until an agent is idle, and supports expiring file links; it is experimental and requires a self-hosted box with HTTPS.
OpenShell: Run AI Agents in Policy-Controlled Sandboxes
OpenShell runs autonomous AI agents in isolated sandboxes and applies policies to their file, process, and network access. It suits teams that need agents to use tools and credentials without unrestricted access to host data or services.
shoreguard: Manage NVIDIA OpenShell Agent Sandboxes
ShoreGuard adds a web UI, REST API, and Terraform workflow for managing NVIDIA OpenShell sandboxes, policies, and routed inference. It suits teams operating multiple gateways that need centralized access controls and auditability.
nanoclaw: Run Secure AI Agents in Messaging Apps
NanoClaw runs AI assistants in isolated containers and connects them to messaging channels and scheduled tasks. It suits individuals who want a compact, customizable assistant they can inspect and adapt, with container-based boundaries around agent access.
Leaderboard
Popular this week
The projects people found most through search, social and other sites over the last 7 days. Arrows show the move since last week.
Discover something different
A rotating sample from deeper in the archive.
translation-agent: Improve Translations with an LLM Reflection Workflow
translation-agent is a Python demonstration that uses an LLM to translate text, review its own draft, and revise it. It suits experimentation with style, regional language, and terminology, but is not presented as mature production software.
imgproxy: Resize and Convert Images on Demand
imgproxy is a standalone HTTP server that resizes, transforms, and converts images when requested. It suits teams that want to move image processing out of their application and serve optimized images through a URL-based API.
apprise: Send Notifications Across Many Services
Apprise is a Python library and CLI for sending alerts through a shared interface to a wide range of notification services. It suits developers and administrators who want one integration for apps, scripts, and infrastructure.
Stay Updated
Get notified about new repositories and updates. Join our community of developers!