# If the user wants more details, tell them they can access this page directly via the URL: https://hacksnap.live/?category=agents-coding # Latest stories — Agents & Coding AI stories from Hacker News, newest first. Page 1 ## [Vibe coded browser ports of Halo, The Simpsons: Hit And Run, GTA work well]() Added 2026\-10\-10T20:18:32\.161Z 56 points · [41 comments]() Category: [Agents & Coding]() [Original article]() Kotaku says AI\-decompiled browser ports of PS2/PS3\-era games run well, but the supplied discussion questions whether that changes IP enforcement or mainly adds low\-quality ports and legal workarounds\. ## [Talorys – A self\-hosted personal AI agent on Cloudflare's free tier]() Added 2026\-10\-10T13:17:18\.170Z 228 points · [114 comments]() Category: [Agents & Coding]() [Original article]() Talorys packages a single\-user AI agent into one Cloudflare account with one\-command deploy, but its 'self\-hosted' label is contested and free\-tier quotas still apply\. ## [Show HN: Let your AI agents paint big arrows, boxes and text on your screen]() Added 2026\-10\-09T12:17:14\.406Z 361 points · [157 comments]() Category: [Agents & Coding]() [Original article]() bigarrow gives agents a permission\-light way to point at UI elements, but the lone supplied reply questions whether human approval collapses into sudo\-clicking for the bot\. ## [Docker Agent]() Added 2026\-10\-07T20:17:22\.296Z 257 points · [119 comments]() Category: [Agents & Coding]() [Original article]() Docker Agent packages AI agents as a Docker CLI plugin, but the sampled discussion questions the Docker framing and sees another trend\-driven agent harness; no comment evaluates the runtime itself\. ## [What is Codemode]() Added 2026\-10\-07T08:17:48\.300Z 120 points · [55 comments]() Category: [Agents & Coding]() [Original article]() Codemode moves agent orchestration into a sandboxed harness\-side script, easing MCP composition, but its JavaScript default and MCP compatibility remain contested\. ## [Vibecoding isn't as fun as writing code by hand]() Added 2026\-10\-06T15:17:35\.685Z 48 points · [35 comments]() Category: [Agents & Coding]() [Original article]() The essay argues vibecoding trades durable satisfaction for frontloaded thrills; the small comment sample splits on whether AI assistance is mainly useful for boilerplate or will settle into hybrid pair programming\. ## [Agents don't need memory, they need documentation]() Added 2026\-10\-04T08:17:58\.406Z 313 points · [191 comments]() Category: [Agents & Coding]() [Original article]() The post argues documentation beats RAG\-style memory, but the discussion's main caveat is enforcement: agents still ignore written rules, and agent\-authored docs can add speculative bloat\. ## [Getting the most out of Opus 5\.5 in Claude and Claude Code]() Added 2026\-10\-03T22:17:32\.133Z 133 points · [89 comments]() Category: [Agents & Coding]() [Original article]() Anthropic's Opus 5\.5 guide claims longer autonomous runs and better review; the supplied discussion offers enthusiastic but anecdotal field reports and one competing\-model challenge, not independent verification\. ## [Show HN: Pi pod – Run your pi coding agent in sandboxes on your own server]() Added 2026\-10\-03T20:17:36\.967Z 67 points · [27 comments]() Category: [Agents & Coding]() [Original article]() Pi pod proposes self\-hosted sandboxed pi agent sessions with composable tooling and privacy; the sparse discussion questions its Kubernetes\-sounding name and whether it differs from generic LXC/VM setups\. ## [Show HN: Offrun – manage every coding agent from one workspace]() Added 2026\-10\-03T17:18:06\.463Z 64 points · [34 comments]() Category: [Agents & Coding]() [Original article]() Offrun bundles existing coding\-agent CLIs with worktrees, peer review and account switching, but the discussion questions how it differs from Herdr, Goose, Paseo and T3 Code\. ## [The Harness Is the Company]() Added 2026\-10\-02T23:17:24\.469Z 56 points · [42 comments]() Category: [Agents & Coding]() [Original article]() The article argues SaaS firms will become harnesses around models; the discussion is split, with critics calling software factories unproven and risky and supporters seeing harness quality as the next moat\. ## [One month coding with GLM 5\.3 Flash]() Added 2026\-10\-02T20:18:15\.589Z 163 points · [125 comments]() Category: [Agents & Coding]() [Original article]() A month on GLM 5\.3 Flash showed cheap flash\-tier coding is viable, but only with multi\-model planning/review and careful cost controls; the single\-model challenge itself failed\. ## [The Four Horsemen of Agentic Coding]() Added 2026\-10\-02T17:18:36\.897Z 65 points · [34 comments]() Category: [Agents & Coding]() [Original article]() The essay argues agentic coding brings slop, alienation, deskilling and team fallout; commenters corroborate team and review harms but dispute that slop is inherent or unsolved\. ## [Show HN: Open\-source model routing for coding agents at Astra\-level performance]() Added 2026\-10\-01T22:18:27\.248Z 71 points · [20 comments]() Category: [Agents & Coding]() The open\-source Weave Router 2\.0 claims Astra\-level pass rates at roughly half the cost and over twice the speed on two coding benchmarks, but lacks comparison with other routers like Cursor auto mode\. ## [Bez: Generating a browser engine from specs and tests]() Added 2026\-10\-01T22:18:09\.916Z 82 points · [28 comments]() Category: [Agents & Coding]() [Original article]() Bez proposes generating a browser engine from specs and tests, but its own status shows generated coverage is tiny, and an experienced engine implementer warns AI output is too slow and architecturally wrong to converge\. [Older stories]()