Loading...
Loading...
Collie: Self-hosted mobile terminal for coding agents on herdr (or tmux/zellij). 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 Collie. This is an automatic list. We have not written a researched verdict for Collie 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.
Forge Orchestrator: Multi-AI task orchestration.
Forge is a governance layer for AI coding agents, built by NXTG.AI for use with Claude Code, Codex CLI and Gemini CLI. Rather than adding more agents or commands, it watches what the agents do: drift detection flags when an agent wanders away from the agreed specification, an auditing component examines tests that pass...
Open-source AI coding agent for the terminal.
KlaatAI, whose terminal coding agent is called KlaatCode, is an AI assistant that routes each request to one of many models under a single subscription. The vendor states that the router covers 47 models from 15 labs and picks the cheapest tier that can handle the task, with automatic failover when a provider has an ou...
Ship features 10x faster.
Shep is an open source orchestrator that runs several AI coding agents in parallel and carries each feature from a one sentence request to a pull request. It works with Claude Code, Cursor, Gemini or any agent that has a command line interface, and it runs locally on Node 22 or later, opening a dashboard on localhost. ...
Make your agents learn from experience.
Agentic Context Engine, usually shortened to ACE, is an open source Python framework from Kayba that lets AI agents improve from their own experience without fine tuning, training data or a vector database. It keeps a Skillbook, a persistent collection of strategies that evolves with every task, and feeds those strateg...
AI agents on autopilot.
AgentUse is an open source agent runtime for recurring work. Agents are defined as plain Markdown files, with model settings and capabilities in YAML frontmatter and the instructions written in natural language, and AgentUse supplies the operating layer around them: the agent loop, tools, durable sessions, schedules, a...
Agor - team command center for all things agentic
Agor is a shared workspace for running AI coding agents as a team. Built by Preset, it places agents such as Claude Code, Codex and Gemini on a multiplayer spatial board anchored to git branches, so people and agents can see each other's sessions, cursors and queued follow ups in real time instead of working in isolate...