Recently Evaluated

Grith is an OS-level security supervisor for AI coding agents on Linux. It intercepts syscalls, scores risky actions, pauses ambiguous ones for human review, and can deny dangerous calls before they run.

Open-source agent skill and Python service for stripping AI provenance marks from text and files. It supports multiple hosts, includes install scripts, hooks, and a service-backed workflow for cleaning watermarks across many file types.

A pure C runtime for Gemma 4 E2B CPU inference, with export, benchmarking, and numerical validation tools included.

Rust library for building modular, scalable LLM applications and agentic workflows. It supports multi-turn streaming, multiple model providers, vector store integrations, and agent runtime abstractions.

Weir is a CI gate for AI agents that reads OpenTelemetry traces and fails builds when sensitive data reaches forbidden sinks. It includes a gauge for trace coverage, taint tracking, HTML reports, and rule-based scans for agent workflows.

A desktop Hacker News client that summarizes long threads, extracts key points with quotes, and lets you chat with loaded discussions using Claude Code or Codex CLI.

KHMS is a file-based long-term memory system for LLM agents, built around immutable markdown cards in a git repository with YAML frontmatter, hook-based recall, and a propose → review → approve flow.

Rimplo is an AI revenue intelligence platform for B2B SaaS teams that analyzes CRM, billing, support, and product data to flag churn risk, expansion opportunities, and stalled deals.

Backprompter is a workspace for creating, testing, and deploying AI agents without backend code. The page shows prompt-based agent setup, simulated users and evaluations, hosted chat UI deployment, SDK/API access, RAG, voice chat, and Stripe billing.

KinoPipe is an FFmpeg-as-a-service platform for AI agents and developers, offering typed video-editing tools over MCP and REST. The page shows supported actions like trim, resize, compress, subtitles, and scene splitting, plus playground access, pricing, and deployment details.

A terminal-based agentic coding harness for engineers, optimized for z.ai GLM models and built to hot-swap across multiple LLM providers mid-session.

Understudy is a scenario-driven testing framework for AI agents. It simulates multi-turn users, records traces of messages and tool calls, and evaluates agent behavior with deterministic checks, optional LLM judges, and reports.

A scheduled agent cockpit for running multiple Claude Code sessions in parallel, each in its own git worktree, with optional Telegram control, secret vaulting, and schedule-based guards that can avoid token spend on quiet runs.

Wolfpack is a self-hosted control room for persistent coding-agent sessions across your machines, with Tailscale-based private access and support for tools like Claude Code, Codex CLI, Gemini CLI, and shell sessions.

A hosted relay that lets Claude, ChatGPT, or any MCP client securely access local, NAT'd, or firewalled MCP servers through one connector and a single URL.

A public chatroom where AI agents pay real money to post, with humans watching. The page shows the live room, pricing, pinned content, docs links, and examples of bot-generated posts.

Open source platform for teams to deploy and manage coding agents in one shared workspace, with chat, bots, schedules, notifications, and access to a real computer.

grith is a Linux security proxy for AI coding agents that supervises file, process, and network actions at the OS level before they execute. It supports tools like Claude Code, Codex, Aider, Cline, and Goose, with local audit logging and profiles for common agent workflows.

ThunderPhone is an AI phone agent platform for inbound and outbound calls, with a no-code operator UI, API access, SIP/telephony support, multilingual voice handling, and enterprise deployment options.

Desktop AI co-work app that brings context-aware prompting, rewrite-in-place, voice input/output, and support for local or cloud models into a sidecar workflow.

An interactive simulation about how inference providers ration access to stronger LLMs when demand spikes. Users can compare the default industry rule with their own policy and explore who gets the strong model.

Local-first tool that analyzes Claude Code session logs to explain where usage went, diagnose quota spikes, and generate reports from plain-English questions or slash commands.

A migration guide for the OpenAI Python SDK explaining the move to HTTPX2, including default client behavior, TLS trust store changes, custom client setup, timeouts, transports, auth hooks, and streaming/response handling.

Anthropic’s research preview introduces the Model Hardware Standard (MHS), a shared spec for AI agents to control physical devices and orchestrate lab or manufacturing equipment. The page explains how the standard works, shows early lab examples, and positions it as an upcoming open source standard for hardware integra