jevc

Compile agent policy prose into deterministic verdict programs: narrow evidence questions for the model, the verdict computed in code.

swarm

Native macOS family tree editor.

ZizkaDB

Audit trail database for AI agents.

TetherPHP

A PHP framework that lets you trace every step from request to response in code

For PHP developers and coding agents seeking a structure they can understand and trace, it provides the Action-Domain-Responder pattern and a clear, class-based request path that can be inspected directly.

NPC-Forge

NPC-Forge is a framework for building conversational agents that run on the CPU without relying on machine learning or LLMs.

jev-cookbook

Runnable question sets for TypeSafe's Jev, an eval harness with measured CLINC150 results, and a linter for the request shapes the API silently mis-reads.

jevlang

A decision tool that takes model classification results as numbers or labels for use in Python conditionals.

Developers building decision flows in Python can ask a model questions about values and use the returned probabilities or labels for conditional branching and decisions about when to hand off to a person.

Motifcode

A terminal coding agent with tool calls and error recovery designed for Motif-3

For developers using Motif-3 for coding tasks, it provides a Claude Code-style terminal environment with a dedicated prompt structure and parser, permission checks, and failure recovery.

AgentTrace

An engine that observes AI agent execution and automatically repairs malformed tool arguments

For developers operating autonomous AI agent pipelines, it visualizes multi-step tool calls and latency bottlenecks, and repairs malformed tool arguments during execution to reduce workflow interruptions.

AutoRAG

AutoRAG: Now your agent can find anything in your computer.

A dead man's switch for cronjobs.

jevals

A Python tool that runs agent evaluations and guardrails in a single request

For teams operating AI agents, it combines multiple typed questions into a single request and returns scores and probabilities, allowing them to evaluate every trace while reducing cost and latency.

MODAK Online

Jump into a browser MMORPG in 1 second.

reader-source

Open-source native macOS AI reading workspace for PDF, EPUB, and TXT with highlights, notes, inline rewriting, book chat, browser panes, and local-first storage.

I am vibe coding a drone

jev-align

An experimental CLI for aligning Jev AI functions with human feedback

For developers creating AI classification and evaluation functions that reflect their own judgment, it selects uncertain cases, requests labels, and improves the functions with GEPA.

DH Tools

A free collection of browser-based tools for PDF, image, and code tasks.

It brings together PDF compression, image conversion, table extraction, JSON validation, and more for users who want to handle document, image, and development tasks quickly.

jev-lint

A linting tool that applies project rules written in everyday language to JavaScript and TypeScript code

Coding agents and developers can write project conventions as natural-language rules, then find possible violations in JavaScript and TypeScript files and review them in a report.

cli

A CLI that maps code dependencies to show AI tools the potential impact of changes.

It helps developers editing code with AI tools analyze project dependencies and identify areas that changes might affect before making them.

daijin

An AI voice-conversation IoT device that controls my home and computer — ESP32-S3 ears/mouth + Mac brain (whisper STT → Claude → TTS) over cloud MQTT - nonasking/daijin

widemelon

Experimental widescreen build of melonDS that expands DS 3D viewports while keeping 2D layers and the touchscreen at native proportions.