Loading...
Loading...
Treg: OpenRouter for agent tools. It is listed under Development & Code on AI Registry as a free tool.
The tools below are approved listings in the same category, ordered by how closely their tags match Treg. This is an automatic list. We have not written a researched verdict for Treg yet, so treat it as a shortlist and check each vendor's pricing page before switching.
Built from each tool's listing. Vendors can update their own listing after claiming it.
Open source, terminal-first AI coding agent with fully transparent multi-model routing.
Albatross is an open source coding agent that runs in the terminal and routes each task across several models at the execution layer. A selector model assigns low, medium or high tiers for the orchestrator and coder roles, adds review and security models, and switches the active coding model accordingly. Every routing ...
Atomic Agent is a local-first AI agent.
Atomic Agent is an open source, local first AI operator that runs on the user's own machine and drives real tools: the browser, the file system, the shell and git. It runs a local model through llama.cpp, so there is no cloud account, no API key and no token bill, and every session is stored on the user's own disk. It ...
A lightweight cli for running single-purpose AI agents.
Axe is an open source command line tool that runs LLM powered agents the way Unix runs programs. Each agent does one focused job, is defined in a TOML file with its own system prompt, model, skill files, context files, working directory and persistent memory, and is run from the terminal. Data is piped in and results c...
Ridiculous speed. Readable code.
B4.run is an open source TypeScript framework for building AI agents in which files are features. A single command scaffolds a new project, and each agent is simply a folder: an index file picks the model and writes the system prompt, and every TypeScript file placed in its tools folder becomes one of the agent's tools...
Run your real agent with and without your skills, MCPs, and rules.
Caliper is an open source evaluation tool that tests whether an agent skill actually helps a coding agent. It runs the real agent with the skill installed where the agent normally looks, then runs it again without the skill, and reports how the pass rate, token use and wall time change, so developers can tell which ski...
Build big projects with Claude.
Chief is an open source command line tool that builds large software projects by running a coding agent in a loop. The developer describes a project as a series of tasks, and Chief works through them one at a time, running the agent until each task is done and making one commit per task. Each iteration starts with a fr...