{ "schema": "tesign-radar/item/1", "generated_at": "2026-09-17T01:56:13.055Z", "lang": "en", "slug": "martin-loop", "url": "https://tesign.com/en/item/martin-loop/", "alternates": { "ko": { "html": "https://tesign.com/item/martin-loop/", "json": "https://tesign.com/item/martin-loop/index.json", "markdown": "https://tesign.com/item/martin-loop/index.md" }, "en": { "html": "https://tesign.com/en/item/martin-loop/", "json": "https://tesign.com/en/item/martin-loop/index.json", "markdown": "https://tesign.com/en/item/martin-loop/index.md" } }, "name": "MartinLoop", "use_label": "Execution-control CLI for coding agents", "one_liner": "Wraps a coding agent with a spend cap and a verifier, so \"I'm done\" comes with an evidence-backed receipt instead of just a claim.", "text": { "why": "A task that looks like a small fix can turn into dozens of retries, a blown budget, and a diff nobody trusts. MartinLoop wraps a coding agent (Claude Code, Codex, and others) with one execution contract — objective, verifier command, budget, iteration cap — around the run. Completion only fires when fresh verifier evidence is bound to that specific run and workspace (\"VERIFIED\" means the configured checks passed, not that the code is bug-free), and every run leaves a receipt you can re-inspect with martin dossier.", "take": "It doesn't try to make the agent smarter — it treats uncontrolled execution by an already-capable agent as the actual problem, which is a sharper framing than most.", "build": [ "Put a hard budget and attempt cap on a task handed to a coding agent", "Bind an independent verifier command (e.g. npm test) so completion needs passing evidence, not just a claim", "Compare outcomes across different agents using the same receipt format" ], "who": [ { "role": "A developer who hands tasks to a coding agent and has to review the results", "situation": null }, { "role": "A team that's been burned by an agent run costing more than expected", "situation": null }, { "role": "Anyone who wants to compare different agents or models under one governed flow", "situation": null } ], "start": [ { "command": false, "text": "Try it now:" }, { "command": true, "text": "npx -y martin-loop@latest start" }, { "command": true, "text": "npx -y martin-loop@latest demo" }, { "command": true, "text": "cd martin-loop-demo && npm install" }, { "command": true, "text": "npx -y martin-loop@latest run \"describe the task\" --verify \"npm test\" --budget-usd 2 --max-iterations 1" }, { "command": true, "text": "npx -y martin-loop@latest dossier --latest" } ], "caveat": [ "Apache-2.0 · needs Node.js 20+", "The hosted dashboard and team features are still early access (per the official homepage)", "The README states plainly that VERIFIED means the configured checks passed, not that the code is safe to merge" ] }, "cta": { "type": "try", "label": "TRY", "url": "https://martinloop.com/" }, "ready": null, "categories": [ "dev-tools", "ai" ], "categories_confirmed": true, "tags": [ "ai-agents", "coding-agent", "governance", "budget-control", "cli" ], "platform": [ "cli" ], "license": { "spdx": "Apache-2.0", "scope": "permissive", "scope_text": "Commercial use, redistribution OK. Keep notices; mark changes.", "url": "https://spdx.org/licenses/Apache-2.0.html", "note": null, "open_source": true }, "language": "TypeScript", "source_urls": { "canonical": "https://martinloop.com/", "github": "https://github.com/keesan12/martin-loop", "huggingface": null, "app_store": null, "sightings": [ { "source": "github", "url": "https://github.com/keesan12/martin-loop", "posted_at": "2026-09-15T18:00:00.000Z", "hn_url": null } ] }, "numbers": { "as_of": "2026-09-16T21:00:00.000Z", "stars": 130, "stars_unit": "GitHub stars", "stars_checked_at": "2026-09-15T23:33:52.402Z", "stars_observed_since_check": 0, "star_delta_24h": null, "star_delta_7d": 21, "star_delta_30d": 21, "star_delta_unit": "GitHub stars gained in the window, GH Archive events summed to as_of", "spark_14d": [ null, null, null, null, null, null, null, null, null, null, null, null, 21, null ], "hf_likes": null, "hf_likes_observed_at": null, "hn_points": null, "hn_points_observed_at": null, "store": null, "method": "Star total = the value last checked on GitHub (stars_checked_at) + increases observed via GH Archive since. The 24h · 7d · 30d gains are GH Archive hourly events summed to the reference time (as_of). No score of ours." }, "ranks": null, "activity": { "pushed_at": "2026-09-15T03:04:19.000Z", "owner_type": null, "open_issues": null, "contributors": null, "releases_count": null, "latest_release": null, "checked_at": null, "core_checked_at": "2026-09-15T23:33:52.402Z" }, "signals": [], "images": { "og": "https://tesign.com/img/martin-loop-a1cb6e24d0.png", "cover": "https://tesign.com/img/martin-loop-a1cb6e24d0.png", "cover_width": 2400, "cover_height": 1260, "gallery": [ "https://tesign.com/img/martin-loop-a1cb6e24d0.png", "https://tesign.com/img/martin-loop-b377bee9d1.png", "https://tesign.com/img/martin-loop-9c13aa3bac.png" ], "alt": "MartinLoop's homepage headline: \"Watch your AI burn $5.20. Then watch MartinLoop close the loop for $2.30.\"", "tier": 1 }, "dates": { "first_seen_at": "2026-09-15T23:33:09.628Z", "source_created_at": "2026-04-04T05:34:39.000Z", "discovery_hours": 3953.9751744444443, "launch_signal_at": "2026-09-15T18:00:00.000Z", "kept_at": "2026-09-17T01:24:00.699Z", "first_published_at": "2026-09-17T01:24:00.858Z", "updated_at": "2026-09-17T01:26:30.194Z", "ingestion_mode": "live" }, "notes": [ "This file was produced by the same build, from the same data, as the tesign.com item page. The text is editorial; the numbers are stored observations.", "null in the JSON means not observed — never zero. The Markdown writes [unconfirmed] for it.", "Star total = the value last checked on GitHub (stars_checked_at) + increases observed via GH Archive since. The 24h · 7d · 30d gains are GH Archive hourly events summed to the reference time (as_of). No score of ours.", "A summary, not legal advice." ] }