Recently Evaluated

Turns Mermaid diagrams into deterministic explanatory text for coding agents, with benchmark evidence and multiple install/use paths shown on the page.

A public OpenAI documentation page for the Daybreak Blue model, with model documentation embedded in the broader API docs index and navigation to related model and agent resources.

Open protocol for agent-consumable job feeds with MCP-native tools, discovery manifests, schemas, and a live API playground for job search and application flows.

Ambient macOS light strip for AI coding agents. Shows agent state beside the Dock with eight virtual LEDs and supports publishing status over a local CLI/API.

A technical blog post from the Cua repository describing a process-scoped Metal capability shim for macOS VMs that improves llama.cpp performance on Apple Silicon, with benchmark results and reproduction details.

Ante is a self-contained coding agent for the terminal. It ships as a single Rust binary, supports online and offline use, and includes headless, server, and gateway modes for scripting, integrations, and bot workflows.

Anthropic help article explaining how Claude marks generated text with embedded watermarks and signed provenance metadata, plus what the markings cover, how to detect them, and key limitations.

An open 45M-parameter agentic LLM for tiny devices, built for tool calling, device use, and structured extraction. It ships as a 14 MB binary and is positioned for phones, wearables, smart home devices, robots, and other low-RAM hardware.

A voice-driven AI murder mystery game set at Blackwood Manor, where players interview suspects, press them on alibis, and solve a locked-room-style case.

An interactive map of 105 AI labs, grouped by research area, geography, lineage, and valuation, with a table view and filters for browsing the landscape.

A live demo and write-up showing a 3.16M-parameter INT4 transformer running entirely in on-chip memory on a Xilinx Kria KV260 FPGA, with measured token rates and hardware details.

AI shopping agent that reviews product links for price manipulation, review authenticity, and seller reputation, then returns a Tick, Clip, or Skip verdict.

Phinq is an open-source runtime governance layer for AI agents that intercepts tool calls, classifies risk, pauses irreversible actions for human approval, and records decisions in a tamper-evident audit log.

Primus is an autonomous AI researcher that hypothesizes, reads papers, writes code, runs experiments on compute, and drafts research papers. The page shows example tasks, published-paper claims, waitlist access, and positioning for ML research workflows.

VS Code extension that provides one interface for running multiple coding agents, including Claude, Codex, OpenCode, Qwen, and Hermes, with session history, diffs, permissions, and tool-call visibility.

Open-source Go control-plane proxy for AI agents that enforces identity, policy, budgets, and audit for MCP and other upstreams, with anomaly detection that can auto-block compromised agents.

A Rust CLI that renders terminal text effects as a single static binary, ported with byte-exact parity from TerminalTextEffects. The README explains usage, build steps, supported platforms, and the project’s fidelity/performance goals.

Open-source self-hosted inference server for agent workloads, with an OpenAI-compatible API, multi-model serving, and production cluster tooling.

TokenSpend tracks AI coding spend and ties it back to shipped work, with GitHub-based PR attribution, team-level reporting, and a live model router with receipts.

Open-source coding agent that keeps a persistent memory of your repo, with a CLI, self-hosted gateway, model routing, and support for OpenAI-compatible and provider-native endpoints.

A set of 20 Claude Code skills distilled from real engineering failures, each packaged as a short rule set with a pre-flight checklist and install instructions.

Pacific Slate is a self-hosted, model-agnostic multi-agent AI assistant with background work, long-term memory, source tracing, and an interface built around cards and a demo monitor. The page also explains the architecture, agent roles, storage boundaries, and how it connects through MCP and an OpenAI-compatible endpo

unYOLO is a framework for building credential brokers and proxies for AI agents. It keeps provider credentials out of the agent, applies local policy rules, supports timed grants and operator approvals, and includes brokers for GitHub, Hugging Face, and approved Unix commands.

A ProtoLink example that stages autonomous agents in a fictional liability tribunal to study how agent-to-agent communication changes decisions, with replayable traces and HTML reports.