maka vs shepherd
Apache-incubating agent workspace where the append-only run log IS the runtime: desktop, TUI, CLI and Eval are thin clients of one host, and every harness benchmark ships with per-task records. — versus — Runtime substrate that records agent runs as reversible, Git-like execution traces — meta-agents can observe, fork, replay and revert any run before outputs are applied or released.
Both make the run record the primary artifact. Shepherd is a substrate that records any agent's run as a reversible, Git-like trace; Maka builds that log into the harness itself — its UI and recovery are projections of it.
| maka | shepherd | |
|---|---|---|
| Stars | 4.8k | 2.4k |
| Forks | 453 | 206 |
| Language | TypeScript | Python |
| License | Apache-2.0 | MIT |
| Last activity | today | 27 days ago |
| Topics | coding, agents | agents, orchestration |
| Curated connections | 4 | 4 |
maka — the curator's take
Pick Maka if you want a coding-agent harness that treats measurement as the product: every model message, tool call, permission and termination is a RuntimeEvent; the UI, the next prompt and crash recovery are projections of that log; and the project publishes per-task results against other harnesses on the same model with the official verifier. Sessions stay local, you bring the model (API, local, or a gateway). NOT a release yet — no ASF release exists, nightlies are unsigned previews — and NOT the lightest: the discipline is the point. If you want a 100-line agent to read, that's elsewhere on the map.
shepherd — the curator's take
The missing 'version control for agent execution': every run becomes a durable trace you can inspect, fork from any step, replay deterministically, or revert — and workspace outputs are held for review before they're applied. If you're building supervision or meta-agents (agents that manage agents), this is the substrate that makes it tractable. NOT mature: early alpha with a moving API and a fresh paper behind it, and the reversibility guarantee only covers what runs inside its coupled agent+environment model — side effects that escaped to the real world don't revert.