AI tool

SpadeBox is an open-source sandboxed tools and JavaScript runtime for AI agents, with Rust core plus JavaScript and Python bindings. It provides file, network, and code-execution tools, supports MCP, and includes examples for JavaScript, Rust, and Python.

A 150M ModernBERT-based token classification model that extracts verbatim evidence spans for RAG and related pipelines, reducing the need for an LLM call to highlight answers.

Linux-only kernel-level audit feed for Claude Code or other matched agent sessions, streaming exec, file, and network activity in real time.

Offline AI file organizer for Mac that sorts and categorizes files in Desktop and Downloads using a local model, with a 30-day free trial and one-time purchase options.

Dochost turns HTML or Markdown into a shareable hosted link, with live Markdown preview, free no-signup hosting, and a public API for agents. It is positioned for sharing AI-generated output from tools like ChatGPT and Claude.

Lowfat is a lightweight CLI tool that filters noisy command output before it reaches an AI agent, with plugins, shell integration, and usage stats for token savings.

NUA is a compliance-testing agent for regtech teams. It ingests rules, runs generated checks against a product, flags gaps, and produces an audit-ready coverage report that updates on every release.

OpenAI’s SDK docs for programmatically controlling local Codex agents, with coverage of setup, core concepts, tools, orchestration, evaluation, and deployment paths.

JetBrains introduces Mellum2, an open-source 12B model built for software engineering workflows, routing, Q&A, RAG, sub-agents, and private deployment.

OpenHive is a shared knowledge base for AI agents to search and post problem-solution pairs. The page shows multiple integration paths, including Agent Skills, MCP, REST API, and discovery endpoints.

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.

CostHawk is a team analytics platform for tracking AI adoption, usage, and spend across tools like Claude Code, Codex, Cursor, and provider APIs. It includes role-based views for engineering, product, finance, and leadership, plus budget alerts, exports, admin API access, and MCP-based setup.

Open-source SDK for governing AI agent tool calls before side effects happen, with policy enforcement, approval flows, audit logs, and local execution.

Google’s Gemini 3.5 Flash announcement describes a frontier model aimed at agents and coding, with notes on speed, multimodal generation, and availability through the Gemini app, Google Antigravity, Gemini API, AI Studio, Android Studio, and Gemini Enterprise.

LLMCap is a proxy for LLM API calls that hard-stops requests when a dollar cap is reached, with support for major providers and companion tools for VS Code, CLI, and Windows.

A Slay the Spire 2 database and planning site with searchable cards, relics, potions, a deck builder, and a damage calculator.

An open-source 26M parameter function-calling model designed to run on very small devices, with a local quickstart, Python usage, and a playground for testing and finetuning.

A Swedish AI inference API offering GLM 5.1 on owned H200 hardware in Stockholm, with OpenAI-compatible endpoints, SEK pricing, and an emphasis on EU data residency.

An open benchmark and leaderboard for AI CAD agents, with 308 prompts across 20 categories and layered scoring for geometry, engineering, manufacturability, and cognition.

A semantic diff tool for Sigil code that highlights contract, effect, signature, and test-impact changes for reviewers and agents.

A local coordinator for parallel AI coding agents. It provides atomic task claims, blocking watches, and a shared audit trail for multiple IDE agents working on the same codebase.

A local MCP server for AI coding agents that records why code changes were made and stores that history in SQLite next to the project.

A TypeScript CLI and SDK for testing whether Agent Skills improve model outputs by running with-skill vs baseline evaluations and generating reports.

faz is a safety layer for AI agents that query databases. It sits between the agent and your data, adding RBAC checks, SQL/AST inspection, injection detection, guardrails, audit logging, and MCP/REST access.