gooseGeneral-purpose local AI agent in Rust — native desktop app, full CLI and embeddable API — over 15+ providers and 70+ MCP extensions. Block's goose, now an Agentic AI Foundation project.
Why switchBoth are local, bring-your-own-model agents with a desktop app and a CLI. Goose is Block's general-purpose Rust agent with a big extension ecosystem; Maka is the Apache-incubating harness built around an append-only run log and published per-task evals.
Full comparison → shepherdRuntime 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.
Why switchBoth 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.
Full comparison → deepseek-harnessDeepSeek's open agent harness (`dsh`): everything is a plugin, on the Cordis composability runtime, with a local web UI one npx away. Developer preview, MIT, moving fast.
Why switchTwo open agent harnesses with desktop and CLI surfaces and a plugin story. DeepSeek's dsh bets on composability (everything is a plugin); Maka bets on the log and on measured, verifier-checked task completion.
Full comparison → mini-swe-agentThe 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.
Why switchBoth 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.
Full comparison →