DEDUPED Hot AI repos, turned into use cases Get 5 a day

How to fan a task wave out to parallel Codex or Claude Code sessions with Hyperfide

Claim conflict-free tasks and run each in its own sandboxed agent process.

Who it is forA team lead with a spec wave of independent tasks who wants several coding agents working at once without path collisions.

The problemRunning several agents on one codebase risks overlapping edits, and tracking who holds which task is manual.

The outcomeEach claimed task runs in one sandboxed child process, with logs and prompts saved on disk and leases released on failure.

What you need first

  • A Hyperfide binary built or installed from the repository (install steps are not in the README excerpt, so check the full README)
  • A git repository or a project folder you want indexed
  • Codex CLI or Claude Code installed if you plan to use spec run or fleet up
  • OPENROUTER_API_KEY or CENTRA_API_KEY only if you want the optional model-backed features

Steps

  1. Run hyperfide spec lint to confirm the wave is executable.
  2. Run hyperfide spec claim-next so an idle agent takes the next conflict-free task.
  3. Run hyperfide spec run to fan the whole wave out to Codex CLI or Claude Code sessions.
  4. Check the logs and prompts saved on disk for each claimed task.
  5. Run hyperfide spec done on each task only after its evidence checks pass.

Prompt for your agent

In the Hyperfide repository, run `hyperfide spec run` for wave <wave number> using Codex CLI or Claude Code. Report each claimed task, its log location, and its final status. Verify that no two tasks declare overlapping paths before the run starts.

Caveat. The README says parallel work is bounded by the disjointness of declared paths, so tasks with undeclared or overlapping paths can still collide.

Share: X LinkedIn Hacker News Email Copy link

Disclaimer

Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page