Agents fail silently. Fix them fast.

Trace every run. Auto-fix silent failures. Ship confidently.

Trusted by engineering teams at

SpeakVercelClayFramerAngelListTolan
857
on GitHub
Billions
Traces processed / month
Fortune 100
Customers
SOC 2
Compliant

Inspect agent traces.

Detect issues automatically.

Experiment with feature flags.

Raindrop Logs - inspect every agent trace in real time

One workflow, every surface

Log every agent run

Every production run leaves a trail of messages, tool calls, retries, and errors. Raindrop captures it all in one place.

Loved by developers

Here's what developers building with Raindrop are saying

SpeakFramerAvocaGC AIPokeQuadraticBoardytype.aiLexUnstuckSpellbook
Clay.comTolanAngelListBrowserbaseHowieSpiralGRWVercelWebSimMerlinFlint
Image

Andrzej Dąbrowski

@ardabrowski

Hey this is awesome! Finally a product where you can "look at your data" in a beautiful way, not just a soulless dump of jsons for nerds. I've been building sth along those lines for customer support (not observability, and not as polished). I display convo history as blocks, similar to Notion, and you get notion-like collaboration too for feedback. Is this possible in raindrop?

Image

Amjad Masad

@amasad

If you're building an agent, I recommend looking into Raindrop for monitoring. We use it.

Image

Jeremy Fischer

@Jeremy_JFischer

I’ve been using this all day today. Soooo much easier to iterate. Spans, token count, cost, timing, a sane view of each tools input-output.

Image

jason

@jxnlco

Heard it works with your codex subscription. Now you can use codex to build agents as well as inspect them I tried it out yesterday and it works great in the in app browser of the codex desktop app

Image

bani

@banisgh

Observability needs to be more actionable. Raindrop was already one of my most used tools and it just keeps getting better (!)

Image

Reid Draper

@reiddraper

absolute 🔥, all other trajectory viewers are unusable in comparison

Image

Hamel Husain

@HamelHusain

Really like the UX/data viz in some of these Increasingly important for sorting through multi-agent / parallel workflows to tame the trace spagetthi

Image

samyok

@samyok

!! we're using this new sdk to page us every time something breaks

Image

austin petersmith

@awwstn

huge fan of Raindrop, it has been immensely helpful for us and i use it every day. congrats on the round!

Image

Rob Haisfield

@RobertHaisfield

@benhylak @raindrop_ai We recently got an influx of users from China and used Deep Search to make a classifier for "the user speaking chinese" this morning. Raindrop translates them, so we're able to get to know a group of users we'd otherwise have no insight into. Feels like I'm living in the future

Image

Devin Stein

@devstein64

loved the onboarding experience

Image

Jake Colling

@JacobColling

Very good. Immediately useful. Going to be using this as default for local agent work now Also looking at instrument Claude code sessions with it to improve skills etc

Image

Danny Aziz

@DannyAziz97

@aviflombaum I’m a huge fan of @raindrop_ai for agent monitoring

Image

Scott Stevenson

@scottastevenson

@jmwind @benhylak We are loving Raindrop!

Image

Jake Colling

@JacobColling

This is very well done. Built in chat that plugs into your local codex/claude is perfect. Need someone to make this for general otel too

Image

Pratyush Rai

@pratyush_r8

This is insanely cool. 🔥🔥 One of the best products out there (by far) for anyone building agents just released an OSS version to play with. We’ve already been using Raindrop heavily across Thine / Merlin. Excited to now use it across personal projects too.

Image

Mitch

@mitchellhynes

Spellbook has been using this for weeks and it feels like magic. It raises silent bugs daily. Feels like my agent is a team member that advocates for itself telling us the most important bugs for us to fix.

Image

Rob Haisfield

@RobertHaisfield

Raindrop feels like extremely futuristic software. It lets you explore user intent and agent trajectories in a way that didn't feel possible years ago. Big fan of them. Every part of what they've built is thoughtful, solving design problems for a new kind of observability.

Image

Sam Whitmore

@sjwhitmore

once again the @raindrop_ai is ahead of the curve…imagine searching for expensive, error prone, or slow tool calls across all your agent traces. nothing like this exists yet

Image

Evan Goldschmidt

@evangoldschmidt

@tolanworld runs on raindrop. highly recommend

Image

austin petersmith

@awwstn

just made a feature request for @raindrop_ai and they shipped it in less than 3 hours

Image

Peter

@peter58587

This is actually incredible. I've been building out a project that involved running Pi in a cloudflare container, it's been a nightmare locally to try and get decent observability on what's happening and to get a feedback loop going. This really came at the perfect time!

Image

Nikita 🤙

@Hormold

nice, it works awesome for voice agents too!

Image

Guillermo Rauch

@rauchg

@benhylak @raindrop_ai awesome

Image

Jean-Michel Lemieux

@jmwind

@benhylak Big fan of raindrop ! 💪🏼

Image

nader dabit

@dabit3

Such a nice idea. we need this for @DevinAI for Terminal @MattSchrage @alexkaplan0 👀

Image

Walden

@walden_yan

Agents finding bugs in agents and tagging another agent to fix those agents Welcome to the singularity

Image

Stew Fortier

@stewfortier

It's difficult to overstate how insanely useful @raindrop_ai is, and it just keeps getting better

Image

Stefanos

@titanas

Raindrop will be remembered as the company who did to AI infra what the Mac did to the personal computer. It’s a matter of time until frontier labs recognize the value and make a move.

Image

Bardia

@thepericulum

Happy customers

Image

Justin

@JustinBleuel

Easily my favorite tool to discover, analyze, and solve agent issues @clay

Image

Nathan Baschez

@nbaschez

This is awesome We @lexdotpage are very happy customers of @raindrop_ai!

Image

Lukas Maschmann

@lukvsm

finally somebody built this

Image

Patrick Ma

@mapeiyuan

Congrats on the launch! Have been building many versions of this from scratch for various projects, and now I can finally use a unified tool for it.

Workshop

The open-source local development tool for AI agents. Inspect traces, replay runs, and debug failures from localhost.

$ curl -fsSL https://raindrop.sh/install | bash

Customer story

How Speak builds agents for 15M learners.

Andrew Hsu, CTO of Speak, on how his team uses Raindrop to monitor and continuously improve the agents behind a language app used by millions.

Security for production agents.

Full visibility into your agents, backed by the security guarantees your organization already runs on.

SOC 2 Compliance

SOC 2 Type II compliant, independently audited each year. Full reports available in our Trust Center.

View our Trust Center →

PII Guard

Intelligent server-side PII redaction keeps sensitive user data protected.

Enterprise Ready

SSO, audit logs, access controls, procurement support, and dedicated implementation help.

Self-HostingBeta

Run Raindrop in your own cloud when your deployment requires it.

Learn more →

Pricing

Get started for free.

Start with a free trial. Upgrade as you grow.

Startup

14-day free trial
$59/mo

$0.001 / event

Start free trial
  • Slack Notifications
  • Signals
  • Search
  • Tracing
  • User Tracking
Most popular

Pro

$399/mo

$0.0007 / event

Get started
  • Everything in Startup
  • Triage Agent
  • Issue Detection
  • Custom Signals
  • Experiments
  • Semantic Search

Enterprise

Contact Us

Custom Pricing

Talk to sales
  • Everything in Pro
  • Audit Logs
  • Snowflake/BigQuery Exports
  • SSO/SAML Login
  • Edge‑PII Redaction
  • Priority Support
  • SLA Guarantees

Have special requirements or need a custom deployment? Get in touch with our team.

Stop guessing. Start tracking.

Store traces. Get alerts. Run experiments.