{"slug": "agentsview", "name": "agentsview", "category": "observability", "category_name": "Monitoring and analytics", "description": "Local tool for browsing AI coding agent sessions, transcripts, and token usage.", "recommenders": 5, "commenters": 5, "warners": 0, "score": 4.719, "rising": 1.02, "first": "2026-06-03", "latest": "2026-10-19", "why": "Recommended for its usage and token-cost metrics and searchable transcripts across most coding agents, built on local conversation files instead of a proxy.", "why_is_quote": false, "has_verdict": true, "sentiment": {"recommend": 5, "neutral": 1, "compare": 0, "warn": 0}, "spark": [0, 0, 0, 0, 0, 0, 0, 1, 2, 1, 0, 1], "listed": true, "loved": ["Usage metrics", "Transcript browsing"], "caveat": "Agent filtering", "short_quote": "I can highly recommend https://agentsview.io/ for a way to dig into your LLM usage.", "icon": false, "domain": null, "github_repo": "github.com/kenn-io/agentsview", "official_url": "https://agentsview.io/", "pricing": "unknown", "aliases": ["agentsview"], "verdict": [{"text": "Recommended for its usage and token-cost metrics", "cites": [{"id": 789838032, "item_id": 49364877, "url": "https://news.ycombinator.com/item?id=49364877", "by": "joshstrange", "date": "2026-08-19", "stance": "recommend", "quote": "I can highly recommend https://agentsview.io/ for a way to dig into your LLM usage.", "excerpt": "I can highly recommend https://agentsview.io/ for a way to dig into your LLM usage. It reads your local conversation files and provides a ton of visualizations as well as the ability to dig into each conversation and see all the tool calls/etc. It's incredibly powerful.", "context": "", "use_case": "analyzing coding agent usage", "switched_from": "", "story": "Show HN: Frugal Tokens \u2013 explore costs and usage across coding agents"}, {"id": 783310944, "item_id": 48956934, "url": "https://news.ycombinator.com/item?id=48956934", "by": "mlrtime", "date": "2026-07-18", "stance": "recommend", "quote": "use one of the many token/session recording tools (I like agentsview)", "excerpt": "Yes, it's close to 100x and it's easy to calculate this. Take a $10 claude sub and fill it with Fable/Opus for a month (meaning use all your tokens) and then use one of the many token/session recording tools (I like agentsview). It will show you how much your token cost is at current rates if using an api. I use the $20 plan and I don't use all my tokens, and am around 50x.", "context": "", "use_case": "tracking token costs", "switched_from": "", "story": "Mozilla: The state of open source AI"}, {"id": 774099536, "item_id": 48381221, "url": "https://news.ycombinator.com/item?id=48381221", "by": "timhigins", "date": "2026-06-03", "stance": "recommend", "quote": "I recommend https://github.com/wesm/agentsview - its quite good, has usage metrics and nice viewer/search for transcripts from most agents.", "excerpt": "I recommend https://github.com/wesm/agentsview - its quite good, has usage metrics and nice viewer/search for transcripts from most agents.", "context": "", "use_case": "agent usage metrics and transcripts", "switched_from": "", "story": "Paseo \u2013 Beautiful open-source coding agent interface (desktop, mobile, CLI)"}]}, {"text": " and searchable transcripts across most coding agents,", "cites": [{"id": 774099536, "item_id": 48381221, "url": "https://news.ycombinator.com/item?id=48381221", "by": "timhigins", "date": "2026-06-03", "stance": "recommend", "quote": "I recommend https://github.com/wesm/agentsview - its quite good, has usage metrics and nice viewer/search for transcripts from most agents.", "excerpt": "I recommend https://github.com/wesm/agentsview - its quite good, has usage metrics and nice viewer/search for transcripts from most agents.", "context": "", "use_case": "agent usage metrics and transcripts", "switched_from": "", "story": "Paseo \u2013 Beautiful open-source coding agent interface (desktop, mobile, CLI)"}, {"id": 802363600, "item_id": 50147725, "url": "https://news.ycombinator.com/item?id=50147725", "by": "chopete3", "date": "2026-10-19", "stance": "recommend", "quote": "This is the best one I found", "excerpt": "This is the best one I found https://github.com/kenn-io/agentsview It is a not proxy. It can clearly show whats going on across all agents. The proxy's are generally inconvenient and yet another point of failure. I think the author got to the resort option quickly", "context": "", "use_case": "viewing activity across agents", "switched_from": "", "story": "If you don't run your own LLM proxy, how do you know whats going on?"}, {"id": 789838032, "item_id": 49364877, "url": "https://news.ycombinator.com/item?id=49364877", "by": "joshstrange", "date": "2026-08-19", "stance": "recommend", "quote": "I can highly recommend https://agentsview.io/ for a way to dig into your LLM usage.", "excerpt": "I can highly recommend https://agentsview.io/ for a way to dig into your LLM usage. It reads your local conversation files and provides a ton of visualizations as well as the ability to dig into each conversation and see all the tool calls/etc. It's incredibly powerful.", "context": "", "use_case": "analyzing coding agent usage", "switched_from": "", "story": "Show HN: Frugal Tokens \u2013 explore costs and usage across coding agents"}]}, {"text": " built on local conversation files instead of a proxy.", "cites": [{"id": 802363600, "item_id": 50147725, "url": "https://news.ycombinator.com/item?id=50147725", "by": "chopete3", "date": "2026-10-19", "stance": "recommend", "quote": "This is the best one I found", "excerpt": "This is the best one I found https://github.com/kenn-io/agentsview It is a not proxy. It can clearly show whats going on across all agents. The proxy's are generally inconvenient and yet another point of failure. I think the author got to the resort option quickly", "context": "", "use_case": "viewing activity across agents", "switched_from": "", "story": "If you don't run your own LLM proxy, how do you know whats going on?"}, {"id": 789838032, "item_id": 49364877, "url": "https://news.ycombinator.com/item?id=49364877", "by": "joshstrange", "date": "2026-08-19", "stance": "recommend", "quote": "I can highly recommend https://agentsview.io/ for a way to dig into your LLM usage.", "excerpt": "I can highly recommend https://agentsview.io/ for a way to dig into your LLM usage. It reads your local conversation files and provides a ton of visualizations as well as the ability to dig into each conversation and see all the tool calls/etc. It's incredibly powerful.", "context": "", "use_case": "analyzing coding agent usage", "switched_from": "", "story": "Show HN: Frugal Tokens \u2013 explore costs and usage across coding agents"}]}, {"text": " The only reported problem is one user who couldn't get filtering by agent to work", "cites": [{"id": 775627651, "item_id": 48476728, "url": "https://news.ycombinator.com/item?id=48476728", "by": "joshstrange", "date": "2026-06-10", "stance": "neutral", "quote": "Hmm, I tried that and made the config file change but it didn't work for me.", "excerpt": "Hmm, I tried that and made the config file change but it didn't work for me. I just see: DATE INPUT OUTPUT CACHE_CR CACHE_RD COST MODELS ---- ----- ------ -------- -------- ---- ------ 2026-06-09 142015 85315 321224 6880110 $10.96 claude-fable-5, gpt-5.5, claude-haiku-4-5-20251001 I tried to filter down to just fable (or 5.5 so I could deduct it) but the `--agent` flag doesn't seem to work how I'd expect... I think t", "context": "", "use_case": "token usage tracking", "switched_from": "", "story": "Claude Fable 5"}]}, {"text": " and saw cost figures that differed from ccusage.", "cites": [{"id": 775627651, "item_id": 48476728, "url": "https://news.ycombinator.com/item?id=48476728", "by": "joshstrange", "date": "2026-06-10", "stance": "neutral", "quote": "Hmm, I tried that and made the config file change but it didn't work for me.", "excerpt": "Hmm, I tried that and made the config file change but it didn't work for me. I just see: DATE INPUT OUTPUT CACHE_CR CACHE_RD COST MODELS ---- ----- ------ -------- -------- ---- ------ 2026-06-09 142015 85315 321224 6880110 $10.96 claude-fable-5, gpt-5.5, claude-haiku-4-5-20251001 I tried to filter down to just fable (or 5.5 so I could deduct it) but the `--agent` flag doesn't seem to work how I'd expect... I think t", "context": "", "use_case": "token usage tracking", "switched_from": "", "story": "Claude Fable 5"}]}], "praise": [{"label": "Usage metrics", "summary": "Shows token usage, visualizations, and what usage would cost at API rates.", "quotes": [{"id": 789838032, "item_id": 49364877, "url": "https://news.ycombinator.com/item?id=49364877", "by": "joshstrange", "date": "2026-08-19", "stance": "recommend", "quote": "I can highly recommend https://agentsview.io/ for a way to dig into your LLM usage.", "excerpt": "I can highly recommend https://agentsview.io/ for a way to dig into your LLM usage. It reads your local conversation files and provides a ton of visualizations as well as the ability to dig into each conversation and see all the tool calls/etc. It's incredibly powerful.", "context": "", "use_case": "analyzing coding agent usage", "switched_from": "", "story": "Show HN: Frugal Tokens \u2013 explore costs and usage across coding agents"}, {"id": 783310944, "item_id": 48956934, "url": "https://news.ycombinator.com/item?id=48956934", "by": "mlrtime", "date": "2026-07-18", "stance": "recommend", "quote": "use one of the many token/session recording tools (I like agentsview)", "excerpt": "Yes, it's close to 100x and it's easy to calculate this. Take a $10 claude sub and fill it with Fable/Opus for a month (meaning use all your tokens) and then use one of the many token/session recording tools (I like agentsview). It will show you how much your token cost is at current rates if using an api. I use the $20 plan and I don't use all my tokens, and am around 50x.", "context": "", "use_case": "tracking token costs", "switched_from": "", "story": "Mozilla: The state of open source AI"}, {"id": 774099536, "item_id": 48381221, "url": "https://news.ycombinator.com/item?id=48381221", "by": "timhigins", "date": "2026-06-03", "stance": "recommend", "quote": "I recommend https://github.com/wesm/agentsview - its quite good, has usage metrics and nice viewer/search for transcripts from most agents.", "excerpt": "I recommend https://github.com/wesm/agentsview - its quite good, has usage metrics and nice viewer/search for transcripts from most agents.", "context": "", "use_case": "agent usage metrics and transcripts", "switched_from": "", "story": "Paseo \u2013 Beautiful open-source coding agent interface (desktop, mobile, CLI)"}]}, {"label": "Transcript browsing", "summary": "Lets users search transcripts and inspect each conversation, including tool calls.", "quotes": [{"id": 789838032, "item_id": 49364877, "url": "https://news.ycombinator.com/item?id=49364877", "by": "joshstrange", "date": "2026-08-19", "stance": "recommend", "quote": "I can highly recommend https://agentsview.io/ for a way to dig into your LLM usage.", "excerpt": "I can highly recommend https://agentsview.io/ for a way to dig into your LLM usage. It reads your local conversation files and provides a ton of visualizations as well as the ability to dig into each conversation and see all the tool calls/etc. It's incredibly powerful.", "context": "", "use_case": "analyzing coding agent usage", "switched_from": "", "story": "Show HN: Frugal Tokens \u2013 explore costs and usage across coding agents"}, {"id": 774099536, "item_id": 48381221, "url": "https://news.ycombinator.com/item?id=48381221", "by": "timhigins", "date": "2026-06-03", "stance": "recommend", "quote": "I recommend https://github.com/wesm/agentsview - its quite good, has usage metrics and nice viewer/search for transcripts from most agents.", "excerpt": "I recommend https://github.com/wesm/agentsview - its quite good, has usage metrics and nice viewer/search for transcripts from most agents.", "context": "", "use_case": "agent usage metrics and transcripts", "switched_from": "", "story": "Paseo \u2013 Beautiful open-source coding agent interface (desktop, mobile, CLI)"}]}, {"label": "Multi-agent coverage", "summary": "Shows activity across all or most coding agents in one place.", "quotes": [{"id": 802363600, "item_id": 50147725, "url": "https://news.ycombinator.com/item?id=50147725", "by": "chopete3", "date": "2026-10-19", "stance": "recommend", "quote": "This is the best one I found", "excerpt": "This is the best one I found https://github.com/kenn-io/agentsview It is a not proxy. It can clearly show whats going on across all agents. The proxy's are generally inconvenient and yet another point of failure. I think the author got to the resort option quickly", "context": "", "use_case": "viewing activity across agents", "switched_from": "", "story": "If you don't run your own LLM proxy, how do you know whats going on?"}, {"id": 774099536, "item_id": 48381221, "url": "https://news.ycombinator.com/item?id=48381221", "by": "timhigins", "date": "2026-06-03", "stance": "recommend", "quote": "I recommend https://github.com/wesm/agentsview - its quite good, has usage metrics and nice viewer/search for transcripts from most agents.", "excerpt": "I recommend https://github.com/wesm/agentsview - its quite good, has usage metrics and nice viewer/search for transcripts from most agents.", "context": "", "use_case": "agent usage metrics and transcripts", "switched_from": "", "story": "Paseo \u2013 Beautiful open-source coding agent interface (desktop, mobile, CLI)"}]}, {"label": "No proxy", "summary": "Reads local conversation files, so it doesn't add a proxy as another point of failure.", "quotes": [{"id": 802363600, "item_id": 50147725, "url": "https://news.ycombinator.com/item?id=50147725", "by": "chopete3", "date": "2026-10-19", "stance": "recommend", "quote": "This is the best one I found", "excerpt": "This is the best one I found https://github.com/kenn-io/agentsview It is a not proxy. It can clearly show whats going on across all agents. The proxy's are generally inconvenient and yet another point of failure. I think the author got to the resort option quickly", "context": "", "use_case": "viewing activity across agents", "switched_from": "", "story": "If you don't run your own LLM proxy, how do you know whats going on?"}, {"id": 789838032, "item_id": 49364877, "url": "https://news.ycombinator.com/item?id=49364877", "by": "joshstrange", "date": "2026-08-19", "stance": "recommend", "quote": "I can highly recommend https://agentsview.io/ for a way to dig into your LLM usage.", "excerpt": "I can highly recommend https://agentsview.io/ for a way to dig into your LLM usage. It reads your local conversation files and provides a ton of visualizations as well as the ability to dig into each conversation and see all the tool calls/etc. It's incredibly powerful.", "context": "", "use_case": "analyzing coding agent usage", "switched_from": "", "story": "Show HN: Frugal Tokens \u2013 explore costs and usage across coding agents"}]}, {"label": "Works well", "summary": "Users call it the best option they found and say it works well.", "quotes": [{"id": 802363600, "item_id": 50147725, "url": "https://news.ycombinator.com/item?id=50147725", "by": "chopete3", "date": "2026-10-19", "stance": "recommend", "quote": "This is the best one I found", "excerpt": "This is the best one I found https://github.com/kenn-io/agentsview It is a not proxy. It can clearly show whats going on across all agents. The proxy's are generally inconvenient and yet another point of failure. I think the author got to the resort option quickly", "context": "", "use_case": "viewing activity across agents", "switched_from": "", "story": "If you don't run your own LLM proxy, how do you know whats going on?"}, {"id": 780452720, "item_id": 48778295, "url": "https://news.ycombinator.com/item?id=48778295", "by": "zaptheimpaler", "date": "2026-07-03", "stance": "recommend", "quote": "I've been running https://github.com/kenn-io/agentsview for this, works well.", "excerpt": "I've been running https://github.com/kenn-io/agentsview for this, works well.", "context": "", "use_case": "searching coding agent history", "switched_from": "", "story": "Show HN: ctx \u2013 Search the coding agent history already on your machine"}]}], "caveats": [{"label": "Agent filtering", "summary": "One user couldn't get the config change or --agent flag to filter results as expected.", "quotes": [{"id": 775627651, "item_id": 48476728, "url": "https://news.ycombinator.com/item?id=48476728", "by": "joshstrange", "date": "2026-06-10", "stance": "neutral", "quote": "Hmm, I tried that and made the config file change but it didn't work for me.", "excerpt": "Hmm, I tried that and made the config file change but it didn't work for me. I just see: DATE INPUT OUTPUT CACHE_CR CACHE_RD COST MODELS ---- ----- ------ -------- -------- ---- ------ 2026-06-09 142015 85315 321224 6880110 $10.96 claude-fable-5, gpt-5.5, claude-haiku-4-5-20251001 I tried to filter down to just fable (or 5.5 so I could deduct it) but the `--agent` flag doesn't seem to work how I'd expect... I think t", "context": "", "use_case": "token usage tracking", "switched_from": "", "story": "Claude Fable 5"}]}, {"label": "Cost accuracy", "summary": "One user saw cost figures that differed completely from ccusage and couldn't tell which was right.", "quotes": [{"id": 775627651, "item_id": 48476728, "url": "https://news.ycombinator.com/item?id=48476728", "by": "joshstrange", "date": "2026-06-10", "stance": "neutral", "quote": "Hmm, I tried that and made the config file change but it didn't work for me.", "excerpt": "Hmm, I tried that and made the config file change but it didn't work for me. I just see: DATE INPUT OUTPUT CACHE_CR CACHE_RD COST MODELS ---- ----- ------ -------- -------- ---- ------ 2026-06-09 142015 85315 321224 6880110 $10.96 claude-fable-5, gpt-5.5, claude-haiku-4-5-20251001 I tried to filter down to just fable (or 5.5 so I could deduct it) but the `--agent` flag doesn't seem to work how I'd expect... I think t", "context": "", "use_case": "token usage tracking", "switched_from": "", "story": "Claude Fable 5"}]}], "who": [], "tags": ["for LLM cost tracking", "for multi-agent users", "local-first"], "use_cases": ["viewing activity across agents", "analyzing coding agent usage", "tracking token costs", "searching coding agent history", "token usage tracking", "agent usage metrics and transcripts"], "compared": [], "makers": [], "threads": [{"url": "https://news.ycombinator.com/item?id=50145507", "title": "If you don't run your own LLM proxy, how do you know whats going on?", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=49364223", "title": "Show HN: Frugal Tokens \u2013 explore costs and usage across coding agents", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=48947825", "title": "Mozilla: The state of open source AI", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=48763462", "title": "Show HN: ctx \u2013 Search the coding agent history already on your machine", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=48463808", "title": "Claude Fable 5", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=48377250", "title": "Paseo \u2013 Beautiful open-source coding agent interface (desktop, mobile, CLI)", "mentions": 1}], "sentiment_by_month": {"2025-11": {}, "2025-12": {}, "2026-01": {}, "2026-02": {}, "2026-03": {}, "2026-04": {}, "2026-05": {}, "2026-06": {"recommend": 1, "neutral": 1}, "2026-07": {"recommend": 2}, "2026-08": {"recommend": 1}, "2026-09": {}, "2026-10": {"recommend": 1}}, "quotes": [{"id": 802363600, "item_id": 50147725, "url": "https://news.ycombinator.com/item?id=50147725", "by": "chopete3", "date": "2026-10-19", "stance": "recommend", "quote": "This is the best one I found", "excerpt": "This is the best one I found https://github.com/kenn-io/agentsview It is a not proxy. It can clearly show whats going on across all agents. The proxy's are generally inconvenient and yet another point of failure. I think the author got to the resort option quickly", "context": "", "use_case": "viewing activity across agents", "switched_from": "", "story": "If you don't run your own LLM proxy, how do you know whats going on?"}, {"id": 789838032, "item_id": 49364877, "url": "https://news.ycombinator.com/item?id=49364877", "by": "joshstrange", "date": "2026-08-19", "stance": "recommend", "quote": "I can highly recommend https://agentsview.io/ for a way to dig into your LLM usage.", "excerpt": "I can highly recommend https://agentsview.io/ for a way to dig into your LLM usage. It reads your local conversation files and provides a ton of visualizations as well as the ability to dig into each conversation and see all the tool calls/etc. It's incredibly powerful.", "context": "", "use_case": "analyzing coding agent usage", "switched_from": "", "story": "Show HN: Frugal Tokens \u2013 explore costs and usage across coding agents"}, {"id": 783310944, "item_id": 48956934, "url": "https://news.ycombinator.com/item?id=48956934", "by": "mlrtime", "date": "2026-07-18", "stance": "recommend", "quote": "use one of the many token/session recording tools (I like agentsview)", "excerpt": "Yes, it's close to 100x and it's easy to calculate this. Take a $10 claude sub and fill it with Fable/Opus for a month (meaning use all your tokens) and then use one of the many token/session recording tools (I like agentsview). It will show you how much your token cost is at current rates if using an api. I use the $20 plan and I don't use all my tokens, and am around 50x.", "context": "", "use_case": "tracking token costs", "switched_from": "", "story": "Mozilla: The state of open source AI"}, {"id": 780452720, "item_id": 48778295, "url": "https://news.ycombinator.com/item?id=48778295", "by": "zaptheimpaler", "date": "2026-07-03", "stance": "recommend", "quote": "I've been running https://github.com/kenn-io/agentsview for this, works well.", "excerpt": "I've been running https://github.com/kenn-io/agentsview for this, works well.", "context": "", "use_case": "searching coding agent history", "switched_from": "", "story": "Show HN: ctx \u2013 Search the coding agent history already on your machine"}, {"id": 775627651, "item_id": 48476728, "url": "https://news.ycombinator.com/item?id=48476728", "by": "joshstrange", "date": "2026-06-10", "stance": "neutral", "quote": "Hmm, I tried that and made the config file change but it didn't work for me.", "excerpt": "Hmm, I tried that and made the config file change but it didn't work for me. I just see: DATE INPUT OUTPUT CACHE_CR CACHE_RD COST MODELS ---- ----- ------ -------- -------- ---- ------ 2026-06-09 142015 85315 321224 6880110 $10.96 claude-fable-5, gpt-5.5, claude-haiku-4-5-20251001 I tried to filter down to just fable (or 5.5 so I could deduct it) but the `--agent` flag doesn't seem to work how I'd expect... I think t", "context": "", "use_case": "token usage tracking", "switched_from": "", "story": "Claude Fable 5"}, {"id": 774099536, "item_id": 48381221, "url": "https://news.ycombinator.com/item?id=48381221", "by": "timhigins", "date": "2026-06-03", "stance": "recommend", "quote": "I recommend https://github.com/wesm/agentsview - its quite good, has usage metrics and nice viewer/search for transcripts from most agents.", "excerpt": "I recommend https://github.com/wesm/agentsview - its quite good, has usage metrics and nice viewer/search for transcripts from most agents.", "context": "", "use_case": "agent usage metrics and transcripts", "switched_from": "", "story": "Paseo \u2013 Beautiful open-source coding agent interface (desktop, mobile, CLI)"}]}