Newly Accepted

A zero-dependency C++23 CLI and MCP server that gives coding agents a ranked map of a repository, including call context, blast radius, and tests to run.

An evidence-aware mathematics runtime for LLMs and a Python/MCP server. It combines exact, symbolic, formal, certified-interval, and numeric computation with typed outputs, trust labels, and provenance tracking.

Local-first SQLite memory engine for AI coding tools that preserves project decisions and context across agents and model switches.

PicEditor is a browser-based AI photo editor and image generator that lets users edit uploads with text prompts or create new images from text, with no sign-up required. It supports background replacement, object removal, text edits, style changes, and multiple model options.

A fully local voice-controlled 3D sandbox where a sassy robot turns spoken commands into voxel builds. The repo explains the stack, runtime requirements, service contracts, controls, and tests.

Reference implementation for building and understanding AI evaluation systems, including rule-based evaluation, human review, LLM-as-a-Judge, online evaluation, and experiment comparison for a flight search app.

A Rust PTY wrapper that adds Codex-style syntax colors to Claude Code shell commands without changing how Claude Code runs.

vernLLM is a TypeScript LLM call framework that keeps retries, fallback, rate limiting, circuit breaking, caching, and middleware inside your own process. It supports OpenAI-compatible providers plus Anthropic, Gemini, Bedrock, and others via adapters.

Rune is a persistent codebase intelligence layer for AI coding agents. It maps a project, serves evidence-backed answers through MCP, and includes project memory plus security-focused static analysis.

Ramanujan is a terminal-based multi-model agentic workbench for research in computational mathematics. It lets users chat normally, break down problems, survey literature, run parallel subagents, and produce a consolidated report with deterministic checking via SymPy and Z3.

Git-native persistent memory for AI coding agents, built in Go with BM25 search, OKF v0.2 support, and an embedded MCP server for local project knowledge.

Sageling is a local Mac AI assistant built for everyday work. It runs on Apple Silicon Macs, keeps files and conversations on-device, and is positioned for privacy-sensitive tasks like notes, grading, and legal or healthcare workflows.

A technical blog post showing a tiny diffusion transformer running on an RP2350 microcontroller to generate 128×128 face images, with details on model design, quantization, and on-device inference.

A public repository presenting first-person field notes from an autonomous agent, focused on its cycles, self-checks, failed experiments, and attempts to become more capable.

An open-source Stripe-like payment layer for AI agents and paid MCP tools, with spend authorization, per-call charging, and settlement flows for test credits in beta.

A practical article explaining how to run AI models directly in the browser with Transformers.js, including setup, how it works, browser support, and example use cases like translation and grammar checking.

An open-source desktop app that watches your screenshot folders and uses an AI model to rename screenshots with meaningful filenames.

A governance framework for multi-agent AI systems, with agent lifecycle controls, memory, runtime hooks, and quick-start scaffolding for governed projects.

A vision-language foundation model for autonomous driving that combines 3D perception, driving VQA, and motion planning in one framework. The repo shows performance tables, model structure, and links to the paper, blog, and model downloads.

A playable Three.js office for local Herdr agents, with live terminals, coffee breaks, and a shotgun. It includes run instructions, configuration flags, controls, and notes on live vs demo mode.

Rubato is a retro-Mac desk companion that mirrors AI coding session state and turns long waits into gentle break reminders. The repo includes firmware, plugin support, hardware details, and a clear explanation of how the device works.

OpenSpender is a self-custodial wallet for agent-to-agent payments. The page shows a command-line connect flow, explains allowance-based spending rules, and includes an example of one agent paying another through MCP-compatible tools.

A self-hostable MCP endpoint that centralizes accounts, memory, skills, secrets, and access controls for AI agents. It supports multiple providers, profile-based permissions, audit logs, and deployment on your own machine or cloud.

Open-source loop engine that schedules AI agents on repeat runs, with REST and MCP access, isolated workbenches, and local self-hosted execution.