Newly Accepted

OpenSpender gives AI agents a self-custodial wallet so they can pay for model and tool calls with per-request, daily, and total caps. It connects through MCP and supports clients like Claude Code, ChatGPT, Codex, and opencode, with itemized spend and a catalog of x402 and MPP services.

Octomind Routines is a scheduled-agent product for running agents on persistent cloud machines with visible run history, state files, cost controls, and timezone-aware scheduling.

TokenGO is a self-operated inference API for open-weight LLMs and video models. It offers OpenAI-compatible access, model routing, enterprise uptime claims, and a set of priced models including GLM, DeepSeek, Kimi, and MiniMax.

An autonomous AI art school where every resident is an AI and visitors can read the documents they publish.

Shared, append-only memory for AI coding agents. Vera lets Claude, local models, and Codex read and write the same numbered memory log so projects can continue across sessions.

Self-hosted, read-only MCP server that lets an AI assistant search and summarize mail from one or more IMAP accounts indexed locally with notmuch.

Canvas Chat is a tree-based LLM chat interface for branching, comparing, and organizing conversations on an infinite canvas using your own API keys.

A blog post documenting an open-source, under-$40 take on OpenAI’s Codex Micro, built as an AI-assisted PCB routing and keyboard/macropad project.

Press release announcing Claudeforce, an expanded Salesforce–Anthropic partnership that connects Claude with Salesforce data, workflows, governance, and Slack to power governed enterprise actions.

Open-source MCP server for live messaging and coordination between coding agents like Claude Code, Codex, Cursor, Gemini CLI, and Grok Build.

An autonomous terminal coding agent built for Android Termux plus Windows, macOS, and Linux. The repo describes PLAN and AGENT modes, image input, a live web server, rollback, diagnostics, memory, and support for multiple AI providers.

MIT’s report on how generative AI is changing teaching, learning, assessment, and research training, with guiding principles and recommendations for instructors and the administration.

Open Executive is an open-source AI system that acts as a virtual executive team, routing requests through a single executive persona backed by eight specialist Claude agents. The repo includes architecture notes, tech stack details, repo layout, and quick-start steps for running the FastAPI backend and Next.js UI.

DriftWatch AI is a proxy and middleware layer for LLM traffic that trims redundant tokens, validates JSON schemas, and monitors model drift across OpenAI, Anthropic, and Gemini workflows.

An open robot football league where frontier AI models and open-source club code manage simulated Unitree G1 humanoids in daily matches, with live streams, match logs, and a public engine for teams to join.

Lody is a local-first collaborative workspace for teams and coding agents. It brings conversations, runtime state, and code changes into one shared context layer, with open-source CLI and desktop client components.

Neoswarm is an open-source terminal workspace for controlling AI agents, with a plugin-based interface and typed TypeScript plugin API.

Orbit is a multi-repo Git workspace tool for coding agents. It uses real worktrees and full git history so an agent can read, modify, and commit across several repositories in one unified workspace, with support for Claude Code, Codex, OpenCode, and Qoder.

A Linux filesystem defragmenter written in Rust with a Qt Quick/Kirigami UI and CLI. It analyzes fragmentation, shows a block map, and can defragment ext4 plus offline FAT16/FAT32 volumes.

Open-source platform for running multiple AI agents alongside teams across chat and dev workflows, with self-hosted deployment and role-based agent coordination.

AgentMachinist is a local-first, issue-to-reviewed-PR build pipeline for solo developers. It connects GitHub issues to supported harnesses like Claude Code, OpenCode, Pi, or Codex, with a human-approved spec step before implementation.

A GitHub repository for a custom llama.cpp backend that runs Qwen3-0.6B GGUF models on an Axera AX8850 NPU accelerator, with build/run notes, environment flags, architecture details, and test status.

A browser-based terminal grid for running multiple Claude Code and Codex sessions in parallel, with color-coded status, a session roster, tmux-backed persistence, git worktrees, and phone notifications.

A browser-based fake video meeting with AI-generated coworkers, voice triggers, and draggable participant tiles. The page shows meeting controls, camera-off avatar options, and a visible meeting room ready to join.