Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Agent workflows with full observability and time travel: watch every step live, rewind, fork, replay any run. Claude Code, Codex, Gemini, any model or harness.
| Date | Stars |
|---|---|
| 2026-07-31 | 346 |
| 2026-08-02 | 348 |
| 2026-08-06 | 348 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
60.0
growth rate 0.00%/day
# Smithers **Agent workflows you can watch live, rewind, fork, and replay.** [](https://www.npmjs.com/package/smthrs) [](https://github.com/smithersai/smithers/actions/workflows/ci.yml) [](#license) [](https://smithers.sh) [](https://github.com/smithersai/awesome-smithers) Tell your coding agent to do real, multi-step work, then Smithers runs it for minutes or days: watch every step live, gate the risky ones behind human approvals, and rewind, fork, or replay any run. The same workflow runs across Claude Code, Codex, Pi, AI SDK models, and remote sandboxes. **Zero config: you never write a workflow by hand.** Describe the outcome in plain English and your coding agent builds the workflow for you, from the same primitives the built-in pack uses. Prompting *is* the authoring step. *Time travel: fork a run from any earlier frame and branch an alternate timeline. Every step is a database row, so live watching, rewind, and replay are built in.* <img src="./docs/images/why/task-fork.gif" alt="Forking a Smithers run from an earlier frame to branch an alternate timeline" width="1032" /> ## What you get - ✍️ **Zero-config agent workflows**: you don't hand-write workflow files. Describe what you want in plain English and your coding agent authors the workflow, then runs it. - ⏪ **Full observability and time travel**: watch every step live, then rewind, fork, or replay any run from any point. - 🛡️ **Durable runs that survive crashes**: every completed step is persisted the moment it finishes, so a run resumes from where it stopped instead of starting over. - 🧠 **Memory across runs**: wrap tasks in `<Memory>` and agents recall what earlier runs learned, pick up `remember`/`recall` tools mid-task, and retain a digest afterward. Works locally out of the box; connect [Hindsight](https://smithers.sh/guide/setup/semantic-memory) for semantic recall by meaning. - 🔌 **Any agent, any model**: Claude Code, Codex, Cursor, Pi, Antigravity, and more, plus any model through the AI SDK. Swap the harness without rewriting the workflow. - 🛠️ **Higher-quality output**: review loops, human approvals, and evals give agents the structure that real work demands. - 🧩 **A focused workflow pack**: create workflows, author standalone skills, and run docs-driven development; former starters remain available as examples. Your agent can author new ones. ## When to use Smithers | You want to… | Smithers? | | --- | --- | | Get one answer from one prompt | No, call the model directly | | Let a coding agent change a repo across many steps | **Yes** | | Pause for a human approval, then resume later | **Yes** | | Run several agents that review, retry, and converge | **Yes** | | Survive crashes and replay, fork, or rewind a run | **Yes** | Smithers is the durable runtime for *coding-agent* work: when the unit of work is an agent editing a real repository over many steps, and you need that work to be inspectable, approvable, and recoverable. ## Why not just let my agent orchestrate itself? Claude Code, Codex, and the other harnesses already fan out subagents, and for work that fits in one sitting they are the right tool. The fan-out is ephemeral, though: it lives inside one session, one vendor, and one terminal. | Built-in subagent fan-out | A Smithers run | | --- | --- | | Dies when the session ends or crashes | Persists and resumes from the last finished step | | One vendor per session | Claude, Codex, Gemini, and Pi share one workflow | | An approval blocks the terminal | An approval suspends the run durably, overnight if needed | | A bad decision means starting over | Rewind, fork, or replay fr
Excerpt of 14,300 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:49d49d4b9e5ee36a, topic:ai-agents, topic:multi-agent
matched fp:49d49d4b9e5ee36a, topic:llm
matched fp:49d49d4b9e5ee36a, topic:developer-tools