#207207th of 259 in Skills, plugins and prompts
agentlas-os
Task-splitting and specialist-agent staffing for Claude Code, Codex and Cursor
- Stars
- 1.6k
- License
- Apache-2.0
- Last commit
- Oct 2026
- Last release
- Oct 2026
- Language
- Python
Missed the latest GitHub check; these facts may be older.
Overview
Agentlas OS (Hephaestus) installs into coding-agent hosts and splits a request into tasks. It then sources candidate agents for each task from local profiles, a private cloud and the public Hub. Candidates are unranked and the model picks one. The chosen release is pinned by digest, and an independent verifier must pass the result. It also builds portable agents with /hep-build and reads and writes A2A v1.0 agent cards.
Who it is for: Developers on Claude Code, Codex or Cursor who want multi-agent task staffing
Strengths
- Installs into many hosts: Claude Code, Codex, Cursor, Antigravity, OpenCode, Goose and others
- SHA-256-checked installer, no sudo, and the README lists every path it writes
- Picked agent releases are pinned by digest; an independent verifier must pass before a run is done
- Uses standard A2A v1.0 agent cards, with signed-card identity checks for external agents
Weaknesses
- Install is a curl-pipe-bash script that edits existing host configs such as ~/.codex/config.toml
- No backup is written when it edits existing host configs, apart from Codex marketplace changes
- Optional global router appends about 75 lines to each host's global instructions file
- Token-savings and recall figures are the project's own measurements, not independently checked
What it needs
- no GPU
- Needs Claude Code, Codex, Cursor or Antigravity host, Model/API access supplied by the caller
- Models: unknown
Also in Skills, plugins and prompts
See all 259| Rank | Project | Score |
|---|---|---|
| 1 | impeccableDesign skill with 24 slash commands for AI coding agents' frontend output | 96 out of 100 |
| 2 | cavemanCuts token use in coding agents with terse replies and compressed inputs | 95 out of 100 |
| 3 | skillsAgent skills for planning, TDD, debugging and code review | 94 out of 100 |
| #4 | eccAgents, skills, hooks and rules bundle for Claude Code, Codex and other harnesses | 94 out of 100 |
| #5 | oh-my-claudecodeMulti-agent orchestration plugin and CLI for Claude Code | 94 out of 100 |