maka vs mini-swe-agent
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 — The 100-line agent from the SWE-bench team: >74% on SWE-bench Verified with no tools but bash, no config sprawl — the reference minimal harness, adopted by Meta, NVIDIA and Ramp.
Both measure themselves on SWE-bench with the official verifier and publish results. mini-swe-agent is 100 lines and bash; Maka is a full workspace with a durable event log. Opposite ends of the same yardstick.
| maka | mini-swe-agent | |
|---|---|---|
| Stars | 4.8k | 6.9k |
| Forks | 453 | 964 |
| Language | TypeScript | Python |
| License | Apache-2.0 | MIT |
| Last activity | today | 2 days ago |
| Topics | coding, agents | coding, agents |
| Curated connections | 4 | 7 |
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.
mini-swe-agent — the curator's take
The existence proof that most harness complexity is optional: the team that built SWE-bench and SWE-agent asked what a 100x simpler agent loses — the answer is almost nothing (>74% Verified), which is why it became the standard baseline harness for benchmarking models (Ramp's SWE-bench, DeepSWE — where it beats Claude Code and Codex as a harness). Read it to understand agents; use it to evaluate models fairly. NOT a daily driver: no MCP, no skills, no IDE plumbing — by design. If you're choosing a tool to ship features with, this is the control group, not the product.