Newly Accepted

Self-hosted AI gateway in Go that routes requests across 30+ LLM providers through a single OpenAI- and Anthropic-compatible API.

Tilde is a harness SDK for building cloud-deployed AI agents, with a blog walkthrough showing how to build a self-hosted code review agent for GitHub PRs. The page highlights tools, chat integrations, and memory components, and points to a deployable example repository.

An open-source multiplayer agent harness for work, designed for Slack and web-based collaboration with scoped memory, permissions, sandboxes, and admin controls.

An interactive AI experiment where two photorealistic eyes argue about everyday moral scenarios, grounded in the sociology of justification and symbolic boundaries.

Self-hosted OpenAI-compatible mock server for testing LLM integrations without exposing API keys. Includes a hosted instance, local setup, Docker support, streaming, and deterministic responses.

A browser-based AI photo editor that lets visitors remove objects, replace backgrounds, use generative fill, and upscale images without creating an account first.

Open-source CLI that keeps a single coding session in sync across Claude Code and OpenAI Codex CLI, letting you switch between models without losing context or paying for two parallel runs.

An open-source web font system that renders protected text normally for readers while serving a decoy version to scrapers that read raw HTML.

A lightweight API key proxy for self-hosted llama.cpp servers with per-user token usage tracking, rate limiting, and multi-server routing.

Memsprout is a shared AI-context layer for teams. Its docs show an MCP server, team spaces, role-based access, and a quickstart for connecting agents and sharing memories across teammates' clients.

A local MCP server that lets AI apps like Claude Desktop and Codex search, read, create, update, open, trash, and restore macOS sticky notes with permission-based access.

A remote MCP server that lets AI agents manage podcast pods by conversation. It supports token-based access and can create, edit, combine, and generate episodes through clients like Claude Code and other MCP tools.

Local-first coding agent that runs on the user’s machine and can work across the browser, desktop, terminal, and editor surfaces. The repo says it verifies fixes by reproducing failures and re-running assertions, with install instructions for Windows, macOS, and Linux.

A local-first TypeScript toolkit for crash-testing AI agents and MCP servers, replaying failures deterministically, and turning broken traces into regression tests.

SKI is a Mac and Windows voice assistant for AI coding agents. It lets developers talk to tools like Claude Code, Cursor, Codex, Gemini CLI, and OpenClaw, and hear replies spoken back locally on-device.

ZeroShot is a developer tool for monitoring coding-agent sessions, turning sessions and PR reviews into reusable skills, and enforcing team conventions on every PR.

A Linux-only CLI wrapper that lets users switch between isolated Claude Code accounts without re-authenticating, using separate config directories per profile.

A research page on how censorship and behavior transfer during model distillation, with published models, data, evaluation code, and a benchmark called LineageEval.

A GitHub repository that provides an agent skill for rewriting documentation in ASD-STE100 Simplified Technical English, with install steps, examples, and support for multiple AI tools.

Glass is an always-on screen recording app that uses secure, local inference on Apple’s Neural Engine to enrich personal context for you and your agent.

A browser extension for Chrome and Edge that connects a local folder to claude.ai so Claude can read, search, and edit files without a desktop app or API key.

Marker is an AI testing and verification platform for voice agents, with a focus on simulation, transcripts, judgments, and versioned evidence across the workflow.

A lightweight TypeScript resilience layer for LLM calls with retries, timeouts, caching, circuit breaking, typed structured output, and usage tracking across many provider clients.

A Rust-based coding agent built for speed, low memory use, and Claude Code compatibility. The project highlights support for skills, hooks, MCP, plugins, sub-agents, and multiple LLM providers, with terminal, headless, and IDE-facing entry points.