AI tool

A Rust reimplementation of the 1982 ZX Spectrum BASIC runtime, compiled to native binaries and WebAssembly, with a live browser demo. The page frames it as an AI software-engineering experiment and describes the interpreter, editor, screen, keyboard, and runtime behavior it recreates.

Open-source MLOps/LLMOps platform for experiment tracking, model registry, and deployment with an emphasis on data and compute staying under user control.

A file-based protocol and CLI for coordinating multiple AI agents across runtimes, with typed messages, review loops, and shared memory on the local filesystem.

Harbor is a local AI stack and launcher for starting pre-configured agentic coding tools against different backends, with support for tools like Codex, OpenCode, Claude Code, and web-enabled workflows.

A file-backed workflow for resumable coding-agent projects, using Markdown records, a CLI, and bundled workflow skills to keep project state on disk instead of in chat.

A terminal multiplexer built for AI coding agents, with persistent sessions, agent-aware status, remote attach, and workspace/tab/pane management.

Steel’s Agent Traces turns recorded browser sessions into a readable, frame-synced timeline with inline details, markdown export, and API access for AI agent workflows.

Open-source, local MCP-based context layer for AI coding assistants. It scans a codebase, builds a behavioral graph, and aims to improve architectural understanding while reducing input-token use on large repos.

Open-source local compute fabric for AI agents. It runs a single-node K3s stack through Docker Compose, provisions isolated Ubuntu sandboxes, and exposes native MCP support for local agent workflows.

Logbox is a developer tool that captures dev server logs and exposes them through an MCP server so coding agents can search and inspect logs directly.

Open-source local-first AI agent that routes between local and cloud LLMs, learns from escalations, and stores knowledge for future queries. The repo includes a quickstart, setup modes, and a concrete explanation of how it ingests docs and improves over time.

Paid public API for finance built on the Neurobro agent. The docs show API key authentication, a single ask endpoint, tier-based modes, billing, rate limits, errors, examples, and a quickstart.

A CLI guard for MCP stdio servers that checks for stdout pollution, handshake failures, invalid JSON-RPC frames, and startup/runtime issues before clients hit them.

An experimental RAG lab for constrained environments, with configurable document classification, chunking, retrieval, reranking, and chat context assembly. It includes Open WebUI integration and emphasizes debugging retrieval and context failures.

A Commodore 64 chat client for Claude that streams Anthropic responses over a serial-style connection, with a Python proxy and C64-side UI.

A Copilot skill suite that enforces structured coding workflows for AI-assisted development, with design, planning, TDD, debugging, verification, and cleanup steps plus a live task-graph visualization server.

A repository of Claude plugins, managed-agent cookbooks, and connectors for legal workflows like commercial review, privacy, litigation, IP, and regulatory work.

TypeScript middleware that trims or compresses LLM chat history to fit a token budget, with support for OpenAI, Anthropic, and AI SDK integrations.

An interactive lab for tracing how AI-assisted engineering workflows can reach repos, CI/CD, credentials, tools, approvals, and proof trails.

Local push-to-talk dictation for macOS that uses Whisper, stays on-device, and pastes text at the cursor.

An agent-first web browser for automating web tasks, with Playwright integration and a CLI for browser control, page inspection, screenshots, navigation, and file actions.

TypeScript SDK for building agent skills as typed state machines, with workflow steps, schema validation, branching, testing helpers, and packaging into distributable executables.

A research-style demo showing LLM agents evolving through a genetic algorithm to play Pokémon in parallel sandboxed VMs. The page explains the setup, scoring loop, generations, results, and links to the repo and run artifacts.

WUPHF is a local-first AI agent workspace that runs a team of role-based agents with a shared wiki and persistent project memory. It supports Claude Code, Codex, OpenClaw, and local models via OpenCode, with install and build options shown on the page.