{"slug": "humanlayer", "name": "HumanLayer", "category": "ai", "category_name": "AI models and assistants", "description": "", "recommenders": 3, "commenters": 4, "warners": 1, "score": 1.718, "rising": -0.98, "first": "2025-12-29", "latest": "2026-07-23", "why": "HumanLayer's agents/commands (in their .claude/) have boosted my productivity the most.", "why_is_quote": true, "has_verdict": false, "sentiment": {"recommend": 3, "neutral": 0, "compare": 0, "warn": 1}, "spark": [0, 1, 0, 1, 0, 0, 0, 0, 1, 0, 0, 0], "listed": true, "loved": [], "caveat": "", "short_quote": "HumanLayer's agents/commands (in their .claude/) have boosted my productivity the most.", "kind": "", "icon": true, "domain": "humanlayer.dev", "github_repo": null, "official_url": "https://humanlayer.dev", "pricing": "", "aliases": ["HumanLayer"], "verdict": null, "praise": [{"label": "", "summary": "", "quotes": [{"id": 784492480, "item_id": 49030780, "url": "https://news.ycombinator.com/item?id=49030780", "by": "bisonbear", "date": "2026-07-23", "stance": "recommend", "quote": "I am genuinely interested in trying HumanLayer", "excerpt": "To me, this comes down to verifiability. How do we measure the quality of what an agent is doing on our codebase rather than simply measuring task accomplishment? > Verifying quality is orders of magnitude harder than \"did the tests pass\" Agree that agentic grading is the future here. Cognition's Frontier Code is probably the best large public benchmark at this. You attribute agent quality issues to RLVR's binary pas", "context": "", "use_case": "", "switched_from": "", "story": "Why Software Factories Fail"}, {"id": 752309074, "item_id": 47019317, "url": "https://news.ycombinator.com/item?id=47019317", "by": "secbear", "date": "2026-02-14", "stance": "recommend", "quote": "HumanLayer's agents/commands (in their .claude/) have boosted my productivity the most.", "excerpt": "Agreed, my experience and code quality with claude code and agentic workflows has dramatically increased since investing in learning how to properly use these tools. Ralph Wiggum based approaches and HumanLayer's agents/commands (in their .claude/) have boosted my productivity the most. https://github.com/snwfdhmp/awesome-ralph https://github.com/humanlayer", "context": "", "use_case": "", "switched_from": "", "story": "Breaking the Spell of Vibe Coding"}, {"id": 742873776, "item_id": 46429611, "url": "https://news.ycombinator.com/item?id=46429611", "by": "itissid", "date": "2025-12-29", "stance": "recommend", "quote": "Just their thought management git system works pretty well for me", "excerpt": "has anyone had good experience with humanlayer's system/process of management? Just their thought management git system works pretty well for me TBH. https://www.humanlayer.dev/", "context": "", "use_case": "Thought management git system", "switched_from": "", "story": "Stop Claude Code from forgetting everything"}]}], "caveats": [{"label": "", "summary": "", "quotes": [{"id": 768816480, "item_id": 48051030, "url": "https://news.ycombinator.com/item?id=48051030", "by": "rubenflamshep", "date": "2026-05-07", "stance": "warn", "quote": "I used to use some of the humanlayer subagents but they haven't been updated in several months", "excerpt": "Some engineers I work with have had less than desirable results with /simplify but it overall seems to work! I used to use some of the humanlayer subagents but they haven't been updated in several months", "context": "", "use_case": "Agent subagents", "switched_from": "", "story": "Agents for financial services and insurance"}]}], "who": [], "tags": [], "use_cases": ["agent subagents", "thought management git system"], "compared": [{"slug": "claude-code", "name": "Claude Code", "co": 2, "switched_from": 0, "switched_to": 0}], "makers": [], "threads": [{"url": "https://news.ycombinator.com/item?id=49023019", "title": "Why Software Factories Fail", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=48023533", "title": "Agents for financial services and insurance", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=47006615", "title": "Breaking the Spell of Vibe Coding", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=46426624", "title": "Stop Claude Code from forgetting everything", "mentions": 1}], "sentiment_by_month": {"2025-11": {}, "2025-12": {"recommend": 1}, "2026-01": {}, "2026-02": {"recommend": 1}, "2026-03": {}, "2026-04": {}, "2026-05": {"warn": 1}, "2026-06": {}, "2026-07": {"recommend": 1}, "2026-08": {}, "2026-09": {}, "2026-10": {}}, "quotes": [{"id": 784492480, "item_id": 49030780, "url": "https://news.ycombinator.com/item?id=49030780", "by": "bisonbear", "date": "2026-07-23", "stance": "recommend", "quote": "I am genuinely interested in trying HumanLayer", "excerpt": "To me, this comes down to verifiability. How do we measure the quality of what an agent is doing on our codebase rather than simply measuring task accomplishment? > Verifying quality is orders of magnitude harder than \"did the tests pass\" Agree that agentic grading is the future here. Cognition's Frontier Code is probably the best large public benchmark at this. You attribute agent quality issues to RLVR's binary pas", "context": "", "use_case": "", "switched_from": "", "story": "Why Software Factories Fail"}, {"id": 768816480, "item_id": 48051030, "url": "https://news.ycombinator.com/item?id=48051030", "by": "rubenflamshep", "date": "2026-05-07", "stance": "warn", "quote": "I used to use some of the humanlayer subagents but they haven't been updated in several months", "excerpt": "Some engineers I work with have had less than desirable results with /simplify but it overall seems to work! I used to use some of the humanlayer subagents but they haven't been updated in several months", "context": "", "use_case": "Agent subagents", "switched_from": "", "story": "Agents for financial services and insurance"}, {"id": 752309074, "item_id": 47019317, "url": "https://news.ycombinator.com/item?id=47019317", "by": "secbear", "date": "2026-02-14", "stance": "recommend", "quote": "HumanLayer's agents/commands (in their .claude/) have boosted my productivity the most.", "excerpt": "Agreed, my experience and code quality with claude code and agentic workflows has dramatically increased since investing in learning how to properly use these tools. Ralph Wiggum based approaches and HumanLayer's agents/commands (in their .claude/) have boosted my productivity the most. https://github.com/snwfdhmp/awesome-ralph https://github.com/humanlayer", "context": "", "use_case": "", "switched_from": "", "story": "Breaking the Spell of Vibe Coding"}, {"id": 742873776, "item_id": 46429611, "url": "https://news.ycombinator.com/item?id=46429611", "by": "itissid", "date": "2025-12-29", "stance": "recommend", "quote": "Just their thought management git system works pretty well for me", "excerpt": "has anyone had good experience with humanlayer's system/process of management? Just their thought management git system works pretty well for me TBH. https://www.humanlayer.dev/", "context": "", "use_case": "Thought management git system", "switched_from": "", "story": "Stop Claude Code from forgetting everything"}]}