Recently Evaluated

A CLI and Python harness that lets AI agents control a real iPhone through macOS iPhone Mirroring or an Android phone over adb, with OCR, accessibility, and input primitives for automation.

A cross-platform CLI for monitoring live Claude Code sessions, context usage, models, and spawned subagents.

Open-source embodied AI agent that uses a camera, stylus, and dedicated phone to operate iPhone apps like a person would, without APIs, ADB, or software installed on the phone.

Leviath is a Rust-based agent runtime for running structured LLM agents from a single file. It emphasizes context regions, stage-specific models and tools, run journaling, live steering, and the ability to run many agents in one process.

Voidleap Code is a local-first agentic coding desktop app for Mac and Windows. It lets developers run AI coding workflows on their own machine, use their own provider keys or local models, switch models mid-task, and inspect prompts, tool use, context, and cost telemetry.

A governed workflow execution spec for MCP hosts, with fail-closed semantics, version pinning, checkpoint enforcement, and a reference implementation plus conformance suite.

Open-source local-first contract layer and runtime for canonical data, retrieval, durable execution, and agent-facing AI. The repo includes a quick start, capability boundaries, client/runtime notes, and examples for running locally and inspecting providers.

A local SQLite-based memory database for AI agents with graph memory, hybrid search, and a tamper-evident thought/edge journal.

A CLI and TypeScript helper that lets coding agents turn MCP tool usage into scripts, with typed APIs and a skill for Claude projects.

Marginal is an LLM cost-tracking and observability product that attributes spend by customer, feature, model, or any custom field. The page shows a dashboard, pricing logic, SDKs, HTTP API access, and example integrations for TypeScript and Python.

Pay-per-fetch China data and analysis API for AI agents, with x402 micropayments, MCP tools, and live endpoint docs.

An Android-based MCP server that lets AI models remotely control a phone through accessibility, screenshots, and file actions, with optional HTTPS and tunnel support.

Local-first, open-source terminal for managing Claude Code and Codex sessions with auto-resume, quick actions, worktrees, and session transfer tools.

ChatOSS is a desktop app for Ollama users that combines chat, coding, task planning, and agent workflows in one workspace. It supports local models through Ollama, can switch to cloud models, and includes features like repository-aware agents, an integrated Kanban board, and app extensions.

Thumb-sized private AI computer that plugs into a phone, tablet, or PC and uses a built-in Android environment to operate apps, run workflows, and automate tasks while keeping data isolated.

fx is a tiny open-source coding agent and CLI written in Zig. The page shows it as a minimal, model-agnostic tool built for research, embedding, and low-footprint local or cloud use, with WASM support and a shell-like interface.

Curia turns a user’s saved links, articles, and threads into produced audio shows and AI podcasts built around their interests.

A browser-based Sokoban game with a client-side AI solver that finds provably optimal fewest-move solutions for most boards and explains how the solver works.

An MCP server and CLI for shared notebooks for agents, with pull/commit workflows, durable S3 storage, and text-based conflict handling.

A community gallery of Claude Code status lines with rendered previews and one-paste copy options, aimed at developers customizing their Claude Code workflow.

MathCode is a terminal AI coding agent for mathematical formalization: it turns plain-language math problems into Lean 4 theorems and attempts formal proofs, with a persistent Lean REPL and supporting theorem/axiom libraries.

Wild Static is a public AI experience where everyone talks to the same model and shares the same memory. Visitors can send a message, watch the AI respond, and see the conversation evolve over time.

A research site for LittleLearner, a language model trained only on K–5 curriculum data to study how bounded pretraining affects capability, scaling, post-training, and in-context learning. The page includes a live chat demo, model scales, controls, and experiment summaries.

AetherGrid is a Python-based distributed compute orchestration project with API key auth, job lifecycle management, reconciliation, leases, and ADR-driven architecture notes. The snapshot shows a substantial repository with documentation, tests, Docker support, and detailed runtime and security decisions.