Newly Accepted

NoWreck is a CLI verifier that checks whether AI coding assistant claims match the actual code changes using structural analysis rather than another model judgment.

Headroom is a macOS menu bar app that compresses noisy prompt context before it reaches Claude Code and Codex, aiming to cut token usage by about 50% while keeping the original retrievable on demand.

Open-source shared memory layer for multi-agent systems, built around signed, cite-able facts that can be read without an account and integrated via MCP, Python, TypeScript, or REST.

Loopsfinity is an agentic software development platform that maps a codebase, turns PRDs into ticketed plans, writes tests first, and ships changes behind approval gates.

A self-hostable Slack-first agent harness that turns plain-English requests into specs, code changes, adversarial review, and pull requests, with local Docker and Fly deployment paths.

A governed MCP server for exposing existing APIs to AI agents with scoped access, verified identity, and per-call audit traces.

A hands-on build story about giving Claude a physical robot body, using computer-use style tool calls, camera input, memories, and scheduled tasks to control a house robot named Bubbles.

Sightmap is an open YAML format and CLI for maintaining shared runtime context about a web app for AI agents. The repo includes the spec, reference Go implementation, docs, and agent skills for browser use and authoring.

An AI Storyteller built for Vampire: The Masquerade 5th Edition with persistent chronicle memory, VtM 5e rules handling, dice pools, and multilingual play.

Writekin is a Mac app that fine-tunes a local language model on your own writing and uses it to draft and rewrite text in your voice, with all processing kept on-device.

A Lean 4 relational knowledge language for project relationships, rules, and queries, with a Clojure runtime/toolchain and examples inspired by Zanzibar.

CLI and TypeScript SDK for finding, validating, and fixing security vulnerabilities in code, with repository scanning, change review, finding history, and CI support.

A web app for branching AI conversations into a DAG-style chat tree, with model switching, response style controls, chat import/export, and example conversations.

Lee-ai is an open-source AI cursor that acts as a website shopping assistant, pointing out products, framing items, and talking to visitors. The page shows a live demo, a GitHub install command, and notes that it works with a two-line integration and keeps keys server-side.

Heddle is a GitHub repository for a git-native coordination layer for coding agents, using intent leases, isolated worktrees, and gated landings to avoid agents overwriting each other.

Orchard is a managed backend for AI coding agents, letting users describe an app and have an agent connect database, auth, storage, email, analytics, and deployment services without cloud accounts or API keys.

A single-binary software catalog for platform engineering with auto-discovery, dependency graphs, scorecards, and a native MCP server for AI coding agents.

Hotcell is a self-hostable sandbox SDK for AI agents that runs isolated sandboxes on local hardware or servers. The page shows setup, CLI commands, key handling, egress control, and support for containers or microVMs.

Banksia is an open-source Python project for building and running accountable AI teams. The repo shows a CLI install flow, a local console, workflow studio, run monitoring, and support for reusable teams and durable state.

Free hands-on labs for prompt injection and LLM security training, with real models, a context trace view of assembled prompts, and a multi-level Gauntlet challenge.

Aidress is a coordination layer for autonomous AI agents with a live API, Python SDK, CLI, and MCP server for verifying, matching, registering, and reviewing agents.

Ami is a local, open-source AI agent that connects to apps and tools with your own tokens, keeps a universal to-do list, and runs busywork on your behalf. It includes copilot chat and graph memory, and runs on your machine with local data storage.

A GitHub repository for connecting AI agents to a real iPhone so they can call or text you, using a Claude Code plugin and a standalone agent skill/CLI.

Browser automation CLI for AI agents with anti-bot handling, human takeover, parallel multi-session browsing, and isolated multi-account workflows.