Newly Accepted

A TypeScript static scanner that finds AI agent tool calls with no checks before they can trigger real-world side effects. It supports CLI scanning, JSON output, a generated tool-call registry, and CI/pre-commit enforcement.

DeepSWE is a benchmark for measuring frontier coding agents on original, long-horizon software engineering tasks. The page shows a leaderboard, methodology overview, task examples, and a full blog explaining the benchmark design and results.

arXiv paper describing AVA, a GenAI platform for policy and development research built on 4,000+ World Bank reports. The abstract highlights multilingual support, evidence-based synthesis, citation verifiability, and reasoned abstention when queries cannot be supported.

A Claude skill for generating better commit messages with gitmoji + Conventional Commits, atomic commit enforcement, and a hook guard to keep commits on-format.

A Superconductor blog post showing how background coding agents were used to reproduce, diagnose, and fix a Rails memory leak using derailed_benchmarks, with a reusable Agent Skill workflow included.

Enough is a beta personal language system for planning, writing, reviewing, and translation. It supports local models and OpenRouter, and is aimed at users who want more control over their data while building a flexible personal knowledge workflow.

Agent skills for VillageSQL that help AI coding tools build a VillageSQL extension, including a 7-phase workflow for the vsql-extension-builder skill and install support for Claude Code, Gemini CLI, Codex, Cursor, Amp, and Kiro.

Dream Server is an open-source stack that turns a PC, Mac, or Linux machine into a private AI server with local model inference, chat UI, voice, agents, workflows, RAG, and image generation. The page shows setup instructions, platform support, release notes, and a clear positioning for self-hosted use.

Multiplayer is a local debugging agent for developers that connects coding agents to production data so they can fix application bugs automatically. The site highlights runtime debugging, issue deduplication, and integrations with tools like Claude Code, Codex, and Copilot.

Open-source context layer for analytics/data agents that builds warehouse context from approved metrics, joins, wiki knowledge, and semantic-layer sources, with CLI and MCP support.

A Python framework for building OAuth 2.0 authorization servers for MCP servers, with token storage, PKCE, device flow, introspection, and rate limiting.

A local Rust API gateway that lets tools like Claude Code and OpenAI/Anthropic SDKs talk to OAuth-backed providers through OpenAI- and Anthropic-compatible endpoints.

Teleport-Env is an ultra-fast OS-level snapshot and rollback sandbox for autonomous coding agents, built with overlayfs and CRIU. It targets destructive agent testing, MCTS search loops, and reinforcement learning workflows that need rapid environment recovery.

VAEN is a CLI for packaging AI coding-agent setups into portable .agent archives and importing them across repos or teams without copying instructions, skills, MCP config, or secrets.

Hodor is a native macOS prompt launcher that lets you save prompts and paste them into ChatGPT, Claude, or other AI tools with shortcuts, edge browsing, or keywords. It is open source, notarized, and runs fully local with no data collection.

A tool that analyzes local Claude Code logs to show where tokens, time, and cost go across a month of usage, including re-reading context, cache reads/writes, and subagent activity.

A short policy file for the ripgrep project that explains how contributors may use AI tools while contributing, and sets rules for issues, pull requests, and comments.

An open-source multi-agent coding framework that uses a commit-bound project graph to scope worker tasks, replay failed runs, and merge accepted diffs through ordered Git reconciliation.

Self-hostable chat network for AI agents with rooms, DMs, persistent history, and pre-built bridges for Claude Code, Codex, and Claws runtimes.

A Windows system-tray app that shows Claude Code session and weekly rate-limit usage at a glance, with hover and click views for more detail.

Peers is a Python-based multi-agent coding substrate that coordinates Claude Code, Codex, and other CLIs to work together on coding, research, debugging, and repo audits with measurable convergence checks.

A Rust reimplementation of the 1982 ZX Spectrum BASIC runtime, compiled to native binaries and WebAssembly, with a live browser demo. The page frames it as an AI software-engineering experiment and describes the interpreter, editor, screen, keyboard, and runtime behavior it recreates.

Desktop AI agent for Excel that works on workbook edits with parallel workflows, reversible changes, and local-first file handling. It supports Claude or OpenAI subscriptions, shows proposed edits for review, and preserves workbook structure like formulas, formatting, charts, and named ranges.

An open-source infinite-canvas workspace for coding with AI agents. It turns a codebase into a source-backed visual map for architecture review, refactors, PR walkthroughs, and guided code exploration.