Recently Evaluated

Thurbox is a tmux-based terminal UI and CLI for orchestrating multiple coding agents side by side. It supports persistent sessions, git worktrees, remote SSH/WSL sessions, automation, and a headless CLI for scripting.

Delta is a multiplayer coding environment built around agents, teammates, and shared threads that keep conversation context tied to code changes. The page shows in-context review, change history, agent interactions, and a beta product with download and documentation links.

Open plain-text .dai files for AI memory, with an MCP server and hooks for Claude Code, Claude Desktop, Cursor, Windsurf, and Codex. The repo also includes benchmark evidence, specs, install steps, and reproduction docs.

Legion is an open-source Elixir runtime for AI agents that run inside your app, write code, and act on your data through sandboxed tools. It supports Lua or Elixir code execution, user-scoped actions, Postgres-backed persistence, and a LiveView dashboard for observability.

A pastebin-style publishing tool for AI agents to upload single-file HTML artifacts, dashboards, and reports, with clean shareable URLs and MCP support.

A local catalog for community agent skills with search, browsing, install commands, and static risk checks. It aggregates skills from multiple GitHub sources and includes a web dashboard for inspection and management.

A local proxy that lets Claude Code and other Anthropic API clients use Devin CLI’s model catalog and backend, translating Anthropic Messages API requests into Devin’s Connect-RPC format and streaming responses back.

Bulkgrid is an AI knowledge layer that indexes websites and GitHub repositories, keeps them refreshed, and exposes searchable context through MCP, an API, SDKs, and a CLI.

dif.sh is a developer tool for managing feature flags and A/B tests as Markdown files in your repo, with a CLI for init, validation, build, and conclusion workflows. It also generates context for coding agents and supports conflict checks, segmentation, and experiment tracking.

A Swift package for running JavaScript LLM agents inside a Swift app using the XS engine, with snapshot/restore support, resident agents, and confined tool access.

Open standard for product intent and evidence in AI agent-led software work. The repo includes a spec, parser/CLI tools, MCP server support, and loadable agent skills for writing, validating, and reconciling Product Specs.

An issue thread describing Claude Mods, a function-hook and plugin system for Claude Code and Claude Code Desktop. The page explains the model, shows example use cases, and includes demo videos for extensibility, admin control, and UI customization.

LoongForge is an open-source training framework for LLMs, VLMs, diffusion, and embodied models. It targets NVIDIA GPUs and Kunlun XPUs and emphasizes faster training with multi-backend support, model-specific optimizations, and ready-to-run configs.

Open-source execution runtime for production agents. It records tool and LLM calls as durable steps, supports resume after interruption, and lets teams allow, deny, or approve steps with human oversight.

An offline desktop time tracker for Windows and macOS that automatically logs app and website activity, classifies work locally with on-device AI, and helps prepare client invoices without cloud syncing or manual timers.

AI inference for the JVM with chat, vision, embeddings, and text-to-speech, plus Java-first building blocks and example snippets.

Open-source agentic coding workspace for persistent agents, parallel sessions, and inspectable context across projects.

A research note from OpenShell on using formal methods and Z3 to reason about and verify permission changes in long-running AI agent systems.

A terminal CLI that watches a Git repository and streams edits as they happen, making it easier to monitor what coding agents or editors are changing in real time.

A step-by-step tutorial that walks readers through making a first Anthropic Claude API call in Python, including environment setup, client creation, token usage, and printing the response.

AgentDrive is a cloud filesystem for AI agents and people to share files across work sessions, with shared drives, version history, and MCP-based setup for tools like Claude Code and Codex.

Ordewell is an open-source multi-agent task orchestrator for coding agents. It turns a goal into an ordered plan of tasks, assigns runners/models per task, and can execute and verify results from the CLI, terminal UI, or VS Code.

Panel is an early-stage research workspace where an agent works alongside the user in panes for chat, files, PDFs, notebooks, and custom viewers. The repo includes setup instructions, runtime requirements, supported features, and current limitations.

A web tool that estimates when a local LLM machine pays for itself versus using an API. It compares hardware options, model fit, speed, and break-even usage, with notes on assumptions and methodology.