tauHugging Face's Python port of Pi's minimalist coding agent: a real terminal agent with TUI, sessions and skills — built to be READ, with a clean brain/environment/frontend separation.
Why switchThe two readable coding agents, at different altitudes: mini-swe-agent is the 100-line loop that proves harness complexity optional; Tau is the layered harness that teaches where the boundaries go when you DO add TUI, sessions and skills.
Full comparison → OpenManusOpen-source general autonomous agent from the MetaGPT team — the 'Manus without an invite code': browsing, tool use and multi-step task execution from a simple Python core.
Why switchBoth are open, minimal-core autonomous agents you can actually read. OpenManus goes general (browsing, tool use, multi-step tasks); mini-swe-agent goes narrow and measurable — software engineering with bash only, scored on SWE-bench.
Full comparison → openinterpreterTerminal coding agent optimized for low-cost open models — a Rust Codex fork with switchable harness emulation (claude-code, kimi-code, qwen-code…), ACP support and Codex SDK compatibility.
Why switchStandalone open coding agents at two extremes: mini-swe-agent is the 100-line research baseline; Open Interpreter is a production CLI tuned per-model for cheap open weights.
Full comparison → prime-agentSelf-improving coding/research agent around a Recursive Language Model: persistent IPython as the core tool, programmatic subagents, durable harness state it refines via evidence-backed /refine.
Why switchThe two poles of coding-agent design: mini-swe-agent proves 100 lines and bash suffice; Prime Agent bets on a persistent REPL, subagents and self-refining harness state.
Full comparison → jcodeRust coding-agent harness built for footprint: ~28MB per session vs 140-390MB for Codex/Claude Code, instant boot, optional local embeddings — made for running many sessions in parallel.
Why switchTwo minimalisms: mini-swe-agent is pedagogical — 100 lines, bash only, read it in one sitting; jcode is engineered — full harness features with the resource profile of a grep.
Full comparison → makaApache-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.
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 →