traceroot.ai (yc s25)

Spent last Friday at @ycombinator's "accelerate your company with AI" day. Best room I've been in this year. Big takeaway: agents shouldn't be a tool you open. They should be teammates that keep working after you close the laptop. Great to meet @RagavSachdeva (Teaflask), @simulated_land (Asteroid), @itsmarinos (Prized), @rak3sh_m (Zarna), @jwonged (Hypotenuse AI) + Edward Tiong (Readily). Thanks @garrytan @koomen @t_blom for the talk on AI-maxxing your team! 🧵

Great night at Kaiyō Rooftop tonight, thanks to @rhobusiness for hosting. Met so many great founders, including @desno365, @Khaliqgant, Tamish from @cocreate_so, and Alex from Gradient (accounting for startups). Sorry if I missed anyone! SF skyline views didn't hurt either.

Jev instrumentation in @TracerootAI , as promised 👀 `TraceRoot.initialize({ instrumentModules: { typeSafe } });` Each Jev call shows up as a decision span, with tokens, cost and probabilities. traceroot.ai/changelog/2026-…

@typesafeai Jev + @TracerootAI , in practice: Connect your TypeSafe key → select Jev → inspect decisions on your agent traces. Setup guide with screenshots 👇 traceroot.ai/blog/2026-09-25… Jev instrumentation coming next. Stay tuned 👀

Your traces, organized your way TraceRoot.AI (YC S25) now lets you tag traces with your own metadata — then slice by it. → filter traces by any metadata key → choose which columns the trace list shows (incl. a metadata column) → filter builder auto-suggests your keys Find the exact runs you care about, fast. Try it → app.traceroot.ai

TraceRoot.AI (YC S25) now has dashboards for AI agents 📊 Traces for deep dives; dashboards for the big picture — latency, cost, tokens, error rate over time. → live-preview widget builder → time-series charts, any range → every row clicks through to the actual trace CLI access coming soon 🖥️ 👉 app.traceroot.ai

Your coding agent can now check on your production agents 🤖 Want to see how your agents are doing in prod without switching to a dashboard? Stay in your terminal — we built @TracerootAI CLI → traceroot traces list — latest prod traces, any time range → traceroot traces get <id> — full trace tree, errors & I/O inline → traceroot traces export <id> — dump the bundle, hand it to Claude Code / Codex / Cursor to debug Best part: no commands to memorize. Just describe what you want in plain English and your coding agent runs it for you. 👉 traceroot.ai

Advanced trace filtering is live in @TracerootAI 🚀 Thousands of agent traces → the handful that matter, in a couple clicks: - filter any field with explicit operators (=, ≥, ≤) - filter by trace_id - URL-synced, so you can share or bookmark a filtered view It took us a bit longer than we first expected to get basic filtering done properly — but it's worth getting this right, since some things still look much nicer and more convenient in a dashboard than a terminal or Slack channel~ 👀 👉 app.traceroot.ai

650⭐ on GitHub for TraceRoot 🚀 The last few months have been something else - growth picking up fast, new contributors joining every week, 70k+ SDK downloads and climbing. Open-source self-healing layer for AI agents, built in public. Huge thanks to everyone shipping with us 🙏 we're just getting started!

@TracerootAI v0.3.1 is out 🚀 - New: Microsoft Agent Framework integration - Faster trace queries + hardened infra - Public API upgrades & lots of polish More features coming very soon~ github.com/traceroot-ai/trac…

Your trace shows what broke. Our AI agent tells you why — by reading your actual code. 🔍 Connect GitHub, click "AI Assistant" on any trace → it clones the exact repo version that ran, finds the failing line, and traces it to the commit that broke it. 👉 app.traceroot.ai

@TracerootAI v0.3.0 is out 🚀 A ton shipped since our last release: - Rebuilt trace UI — color-coded spans, fullscreen, open-in-new-tab, resizable panels, timeline view - Live trace streaming (SSE) — watch agent runs in real time - Inline images & audio — media renders right in the trace viewer - Cost, tokens & latency everywhere — cache + reasoning breakdown, per-span cost - Huge traces load instantly — gzip, virtualized tree, ClickHouse rebuild - 20+ framework integrations — OpenAI Agents, Claude Agent SDK, Pydantic AI, CrewAI, AutoGen, LlamaIndex, Vercel AI SDK, Bedrock, etc. - New models — GPT-5.5, Gemini 3.5, Opus 4.8, DeepSeek V4, Kimi K2.6, GLM-5.2 Full notes 👇 github.com/traceroot-ai/trac… Huge thanks to all the contributors! 🫶

@TracerootAI now traces @pydantic AI agents, end to end 🐍 Customers asked — so we shipped it. - One-line auto-instrument: `traceroot.initialize(integrations=[Integration.PYDANTIC_AI])` — every agent run, LLM call & tool call. No decorators. - Accurate cost & tokens, cache included - A working example to copy: github.com/traceroot-ai/trac… 👉 pip install traceroot

GLM-5.2 is built for agentic work — frontier coding, open weights, 1M context. 🔥 So we support it in the coolest part of TraceRoot: a self-healing layer for AI agents. A production coding ai agent, could run on GLM-5.2 with your API key, that watches your agent system in production 24/7, catches failures, find the root cause, and tells you exactly how to fix them. Freshly supported by our OSS contributors 👇 github.com/traceroot-ai/trac… thanks @internetDevv and @lqiu03 !

One real customer trace: 67 spans, 24MB. A single lookup scanned 1.59 GiB and took ~3s. AI agents only get bigger. If your observability can't load that fast, it fails you exactly when you need it most. So we rebuilt how TraceRoot loads large traces 🧵

Vercel just went all-in on agents this week ▲ If you're building on the AI SDK, here's how to actually see what your agents do: TraceRoot shipped first-class AI SDK v6 examples — full traces, every tool call, and real cost (cache tokens broken out). 👉 `npm install @traceroot-ai/traceroot`

@TracerootAI just got a major UI overhaul 🎨 - Color-coded span kinds (errors always win red) - Fullscreen + open-in-new-tab for deep traces - Cost, tokens & latency previews everywhere — list, detail, every span on hover From trace list → a single span's cost in a few clicks!

TraceRoot.AI now has much better support for the Claude Agent SDK 🛠️ More founders are building on it — and subagents are the most-loved part. So we made tracing them feel great: • First-class subagent spans + lifecycle • Per-turn token + cost accounting • Smart tool parenting Give it a try traceroot.ai/!

@TracerootAI now has a span timeline view 🚀 Every span as a Gantt-style bar — latency hotspots jump out instantly. Click a bar → jumps to the span in the tree. Works on live traces too, bars stream in as the agent runs!