AI tool

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.

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

An MCP server for AI agents that stores persistent long-term memory in OKF format and searches it with SQLite FTS5.

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.

BoundaryBench is an open-source benchmark for coding agents running under hardened sandbox policies. It compares harnesses like Claude Code, Codex, Terminus 2, and Grok on Terminal-Bench tasks and includes quickstart, policy controls, and result export tools.

MCP server that lets AI agents control labgrid-managed embedded hardware labs through 47 tools, including power, console, flashing, muxing, SSH, and place management.

A local-first Node.js utility that redacts emails, phone numbers, paths, secrets, URLs, and other identifiers from LLM prompts, then rehydrates responses locally using session-based mappings.

An interactive browser city that visualizes how an LLM works, with live transformer mechanics such as tokenization, attention, KV cache, residual stream, and sampling.

Free hands-on labs for prompt injection and LLM security training, with real models, a context trace view of assembled prompts, and a multi-level Gauntlet challenge.

A curated-taste API for architecture, art, design, and photography, with both REST endpoints and a native MCP server for AI agents. It offers search, similarity, provenance, and taste metadata across 2,500+ hand-selected projects, plus free keys and documented pricing.

A fast, private, self-hostable AI chat app for OpenRouter. It supports bring-your-own-key usage, model selection across many providers, attachments, web search, portable history, and both hosted and self-hosted deployment.

LLMIntel is a runtime telemetry and cost dashboard for LLM apps. The live demo shows spend by model, API key, environment, and tag, plus at-risk spend for retiring models and optimization suggestions.

A free public API for LLM pricing, specs, benchmarks, and cost calculations across 1,000+ models. It offers no-auth endpoints, CORS support, an OpenAPI spec, and a LiteLLM-compatible cost map that refreshes daily.

Open-source Chromium fork that aims to keep browser automation and scrapers from being blocked by patching fingerprint surfaces inside the engine. It connects over CDP and is positioned as a drop-in replacement for Playwright, Puppeteer, and other CDP clients.

An MCP server that gives AI agents access to 8,500+ curated awesome lists and 1.3M+ resources, with hosted and local setup options plus tool docs and example queries.

Local-first document AI that extracts structured JSON from PDFs, scans, images, text, and Markdown without sending data to a third-party API. It includes a REST API, CLI, and Web UI, and supports local execution on macOS Apple Silicon and Linux NVIDIA systems.

A Model Context Protocol server for Uptime.com that lets AI assistants manage monitoring checks, alerts, outages, status pages, and account usage through tools and hosted or self-hosted deployment options.

Local-first observability and evaluation layer for production forecasts. Captures forecasts, validates them, computes horizon-aware metrics, and serves a read-only local UI for comparing runs.

Local dashboard for Claude Code sessions with live monitoring, session history, usage charts, resume commands, and LLM usage analysis.

Self-hosted observability and control plane for production and coding AI agents, with live timelines, fleet-wide feeds, token budgets, MCP allow/block rules, and support for Claude Code plus a Python sensor.

AI code review tool that scores code against six decay-risk dimensions inspired by twelve classic engineering books, with book citations, severity labels, and remediation guidance.

Crit is a local-first review tool for AI coding agents, letting users comment on plans and code diffs, iterate through multiple review rounds, and share reviews when needed. It supports several agent ecosystems and can be installed as a single binary.

Tilde is an agent sandbox platform for running AI agents and pipelines on real data with transactional commits, rollback, audit logs, and a versioned filesystem that can compose GitHub, S3, and Google Drive.

Open-source AI sandbox infrastructure for running code, browsing the web, and isolating agent workflows inside disposable microVMs.