Recently Evaluated

A GitHub research project documenting a long-form, multi-model analysis of LLM behavior across Claude, Gemini, ChatGPT, and Grok. The repo includes an executive summary, screenplay, technical white paper, and archive of logs and chat records.

Rust CLI that uses OpenAI Realtime voice input to orchestrate concurrent background coding agents, including Claude Code and Codex CLI, with slug-based task tracking and progress updates.

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.

An open-source Python support agent that uses SynapCores as the agent brain for memory, retrieval, semantic tool routing, and generation. The repo includes a quick start, local Docker setup, example commands, and a traced demo of the agent loop.

An opinionated write-up on where multi-agent systems have and have not delivered value, with concrete comparisons across coding, images, CAD, and BIM, plus a description of Blade’s evidence-first architecture.

A Claude Code skill pack with 171 structured reasoning methods drawn from historical thinkers, designed to route different problem types to specific procedures.

iOS app for local, offline Stable Diffusion image generation on iPhone and iPad, with private prompts and images stored on-device.

Smriti is an open-source system for shared reasoning state across coding agents like Claude Code and Codex. It treats project reasoning like version-controlled state, with local setup, a CLI, backend, and frontend for coordinating multiple agents on the same repo.

A local, read-only observability dashboard for Claude Code with live event streams, session Kanban, token and cost charts, a 3D tool-call graph, and plugin-based widgets.

Open-source AI SEO optimizer CLI that audits pages, generates meta tags, analyzes keyword gaps, and drafts blog outlines. It can run free for audits and uses a KianBot API key for AI-assisted features.

A post about TMA1 v2, a local observability and context-sharing tool for coding agents. It adds an MCP server, hook-based context injection, and cross-agent sharing between Claude Code and Codex.

Chrome extension that extracts AI-generated HTML from ChatGPT, Claude, and Gemini, then previews, downloads, or publishes it to targets like Netlify, GitHub, FTP, or a self-hosted agent.

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 GitHub research project that measures how gpt-4.1 responds when asked to pick a random number between 1 and 100, using 10,000 API calls and comparing the results to a uniform baseline.

An interactive guide for choosing local AI hardware and matching open-weights LLMs to specific builds. It offers budget-based build recommendations, a hardware picker, model-to-hardware compatibility, and a state-of-the-local-AI snapshot.

A PyTorch reference implementation of DeepSeek Sparse Attention from the LLMs-from-scratch project, including a lightweight indexer, top-K token selection, and a GPT-style model with KV-cache support.

CodeGraph is a local code knowledge graph for AI coding agents like Claude Code, Cursor, Codex, OpenCode, and Hermes Agent. It aims to cut token use, tool calls, and runtime by letting agents query pre-indexed code structure instead of scanning files repeatedly.

A Mojo port of the Pi AI Agent Toolkit with a set of runnable examples for chat, coding agents, tool calling, web research, and long-running agent loops.

A browser-based demo where an AI agent writes x86_64 assembly and eBPF to generate Wolfram cellular automata and Mandelbrot fractals inside a real Linux VM, with framebuffer and kernel trace streams exposed live.

An essay arguing that second-person system prompts create attentional overhead and identity fragmentation in agent design, and proposing first-person initialization as an alternative.

Agenvoy is a Go-native multi-model AI agent framework that routes tasks to the best model, shares a common daemon and session across interfaces, and can generate scripts or APIs to extend its toolset.

Optic is an AI feature intelligence platform for SaaS teams. It tracks AI interactions at the account level, surfaces quality and abandonment signals, and sends engineering alerts plus daily CS digests in Slack.

A bilingual satirical idle simulation where you run an AI startup from toy classifiers to near-AGI, managing data, compute, launches, crises, and rivals.

A Torque demo page showing proof-gated, policy-checked production changes for a Kubernetes PostgreSQL workload, with signed evidence, authorization records, and replayable audit artifacts.