Recently Evaluated

A local MCP server that builds a deterministic architecture graph of a codebase so AI coding agents can inspect modules, symbols, routes, dependencies, and cross-repo relationships from source-backed facts.

An MCP server that gives coding agents a compiler-backed graph of a TypeScript codebase, so they can answer structure questions with fewer tokens and exact file-and-line references.

Bootable Rust no_std kernel built as an inference substrate for LLMs, with tensor-native memory allocation, layer-boundary scheduling, and streaming-focused runtime primitives.

Open-source, local-first money agent that finds waste, drafts cancellation or dispute actions, and only proceeds with user approval. It emphasizes consent, a tamper-evident audit trail, and bring-your-own-key operation.

A from-scratch ~1B parameter language model on Hugging Face with open weights, open data, training details, and loading guidance. The page is unusually candid about capabilities, limits, and evaluation.

A monthly poll that asks developers which AI coding agents they use and publishes the results.

An open-source AI agent platform for production workflows, with isolated containers, credential proxying, and support for 100+ business and productivity integrations.

An open-source Python tool that turns multi-persona AI debate into pre-registered, time-anchored predictions and scores each seat against reality with Brier-style calibration. It includes a CLI, sample workflows, docs, and examples, plus a BYOK design for running on your own model key.

A Pomodoro timer for Claude Code that shows a live countdown in the terminal status line and includes a backup alarm, CLI controls, and setup commands.

OpenWiki is a CLI for generating and keeping agent-oriented documentation up to date for a codebase. The repo shows installation, init and update commands, interactive and one-shot usage, and support for multiple model providers.

Bytesalt is an AI QA assistant that helps run testing workflows for web apps and APIs, with prompts for UI/UX audits, functional tests, accessibility, penetration, cross-browser, and cross-device checks.

An early-access AI research assistant that presents a cited mindmap of AI agent safety and alignment research, with expandable nodes, source-backed claims, and built-in verification checks.

Rust-based DAG pipeline engine with a visual node editor for building and running workflows. The repo shows programmatic usage, a UI package, and examples for chaining processors like image loading, grayscale conversion, and saving output.

Loma is a self-hosted AI agents platform for teams, with a Slack interface, web dashboard, scheduled flows, webhooks, and a shared skill library. It supports open models via OpenCode and can pool existing Claude subscriptions.

Open-source tooling that generates private, point-in-time infrastructure snapshots from cloud and on-prem systems into vendor-neutral OSIRIS JSON for audits, diagrams, diffs, CMDB/IPAM/DCIM workflows, and controlled AI/MCP context.

A Claude Code-based operating system for running executive workflows across research, communications, CRM, content, and operations, with a split between a public engine repo and a private data repo.

A local-first backend for AI agents that bundles documents, vector search, cache, queues, and cron jobs into one SQLite file, with optional Postgres support.

Palabre is a terminal-based multi-agent coding assistant that lets you run debates or parallel answers across local and cloud AI CLIs, then exports a Markdown synthesis. It also has a VS Code extension for running the same workflows inside the editor.

fenic is an open-source Python framework for semantic DataFrames, letting you use LLM-powered operators like extract, classify, summarize, and embed inside query pipelines.

Minimal Erlang library for calling OpenAI and Anthropic models, with tool-use support and a built-in JSON encoder/decoder.

Open-source research skill that helps Claude, Codex, and OpenClaw run a more disciplined AI research workflow, from hypothesis and literature review through baselines, leakage checks, analysis, and paper writing.

AI QA agent for startups that reviews PRs and tickets, runs browser tests on staging, and posts a GO/NO-GO decision.

An AI agent built to help manage ADHD-related workflows through Telegram. It connects to calendars, Todoist, Obsidian, web search, browser automation, TTS, and uses memory, sub-agents, and specialist personas for planning and task handling.

A drop-in proxy for Ollama that automatically tunes local LLM requests to reduce RAM use and speed up first-token latency. The page shows install steps, benchmark results, a live dashboard, and a local-only admin UI.