Timbal AI

Build AI agents, workflows, and apps in one stack

Productivity

SaaS

Artificial Intelligence

Visit WebsiteSee on Product HuntTwitter ⧉LinkedIn ⧉

For teams already using separate best-of-breed tools, like LangSmith for evals, Pinecone for retrieval, and their own orchestration layer, what's the actual migration story? "One platform" is compelling when starting fresh but most teams evaluating this have existing infrastructure they'd be replacing, curious whether Timbal is designed to coexist with those or replace them entirely.

Really like how you framed the “0 to 1 vs 1 to 100” gap, it’s exactly the pain point most teams hit. The unified stack approach feels refreshing compared to juggling fragmented tools. Curious to see how Timbal handles scale in real-world enterprise setups, but the open-source core is a strong signal. Excited to see where this goes!

The "one stack" pitch is appealing — the amount of time spent stitching together separate tools for

retrieval, orchestration and observability adds up quickly. How does it handle model switching mid-workflow?

Curious whether you can swap between providers without rebuilding the whole pipeline.

congrats on the launch!

I am curious, why a company would prefer to use Timbal vs Claude or Devin?

Congrats on the launch!!
That's a really cool project, I tried to create a simple agent and it really satisfied my expectations.

But what about token usage? isn't it expensive?

Congrats everyone! Composer will get the attention because it's the flashy front door, but the real value here is what happens after you build something (how it's run, traced, and governed). That's the part most tools skip and it's exactly where projects usually fall apart once they're live.

Consolidating retrieval, orchestration, UI, observability, and evals into one core solves the tool-sprawl problem that quietly eats operations budgets, so this is going straight on my evaluation list.

The tool-stitching problem is so real. Spent way too long gluing together separate tools for orchestration, logging, and UI. Makes total sense to have one platform for all of it. Congrats on the launch 🎉

How does pricing scale as you add more agents and team members, especially once you start hitting heavier eval runs on bigger workloads?

Congrats on the launch! I build AI agents internally for a 40-person company and my current stack is duct tape: prompts in one place, tools in another, deployment somewhere else. One stack for all of it is exactly the pitch that gets me. Question: how do you handle testing before an agent hits production? Rolling back a bad prompt change has burned me more than once, so versioning and evals are what I’d look at first.

the trace-at-every-step answer to Shubham's question is the part that sold me, that's the actual difference between a demo and something a team will trust in production. one thing I'd want to understand before committing though: once retrieval, orchestration, UI, observability and evals all live in one core, how painful is it to rip out just one piece later if a team outgrows it or needs something more specialized, or is the whole pitch that you shouldn't need to

How does Timbal handle versioning when you iterate on agents and workflows, and can you roll back to a previous version if something breaks in production?

Love how you're baking governance and step-level tracing into the runtime itself, turning the usual after-the-fact scramble into something you can just replay and inspect.

Really like the positioning around helping teams move from AI prototypes to production—it feels like a problem a lot of builders eventually run into. I'm curious, after working with customers, what's the most common reason promising AI prototypes never make it to production? Is it usually reliability, observability, governance, or something else that catches teams by surprise?

@pedrolivares — the part that resonates: making the resilience logic — per-step retries, primary→secondary model fallback, human-in-the-loop — a property of the runtime instead of glue code every team rewrites and half-tests.

I've watched agent projects die right in that "between the tools" seam, so having ACE enforce expected behavior at each node and trace every retry/fallback is the piece I'd actually trust in production.

Model-agnostic with the fallbacks baked in is the right call too.

Congrats on the launch!

I spend most of my day talking to enterprise teams who are stuck exactly where you're describing: impressive demo, then six months of stitching together retrieval, observability, and governance before legal will even let it near production. The human in the loop piece is what caught my eye, since "who approved this agent's decision" is usually the question that kills deals late in procurement.

Curious how long your average enterprise sales cycle is now that you've built compliance in from the start, has it actually gotten shorter?

Honestly the part that gets me is that gap after the first demo, thats always where my projects start falling apart lol. so seeing you focus on the production side and not just the shiny prototype is refreshing. quick q on the data side, how do the knowledge bases work? can i connect my own KBs through MCP or does everything have to go through timbals own ingestion? curious how that plays with retrieval before i try moving stuff over.