Recurse
Develop and deploy specialist agents faster
Details
- External ID
- 49850553
- Source
- HN
- Company
- —
- Product
- Recurse
- Website domain
- recurse.run
- Launched
- Sept. 25, 2026
- Cohort
- —
- Upvotes
- 8
- Upvotes percentile
- 0.5015948963317385
- Tags
- —
- Fetched at
- Sept. 29, 2026, 5:01 p.m.
- Updated at
- Sept. 29, 2026, 5:01 p.m.
Description
Hi HN! We are looking to gather some feedback on our serverless agent harness. The admittedly not-so-specific use case is to accelerate agent development and deployment. After building several custom/special-purpose agents for a few customers, we built this to accelerate our workflow at first, and now we are trying to understand whether it could be useful to others.Our driver use case was development of specialist agents with a request/response lifecycle. Think of agents that have a well established input/output contract where they are expected to produce high-quality output (artifacts, responses etc.). Especially when the problem is in some verifiable domain and the LLM can iteratively refine a result to a final value that satisfies constraints or optimizes some goal.The product is a coding agent skill + a serverless execution runtime with a harness that takes in a system prompt + Python functions as tools. The coding agent takes in the requirements from the user, and tries agent variants by executing prompt/tool variants it creates.It works best for cases where you can think of how you can evaluate a candidate agent - when you describe this information to your coding agent, it often does a decent job at building candidate prompts, tools and even benchmarks.Prompts and Python tools that the coding agent creates integrate with a harness that implements an FSM that is tuned to drive an iterative refinement process for verifiable domains. This tuning enables one to use small models like Luna to produce high quality results while keeping costs at a manageable level.Our website is not 100% complete yet (some examples are missing write-ups, not all use cases we tried are there etc.), but the system is operational and docs are there.Thanks!
Enrichment
- Theme
- AI agent frameworks and developer tools
- Vertical
- Horizontal
- Function
- Dev tools
- Audience
- Developer
- AI stance
- AI-native
- Project type
- Commercial product
- Normalized one-liner
- development and deployment platform for specialist ai agents
- Manually corrected
- False
Could you build this?
Partial While wrapping LLM agents via YAML manifests can be scaffolded quickly, building a reliable multi-tenant serverless execution harness with sandboxed code execution and stateful evaluation loops requires non-trivial infrastructure.
What it would actually take: A production implementation requires a secure multi-tenant sandbox runner (using Firecracker microVMs or gVisor/Docker containers) to execute arbitrary tool code safely. It needs an orchestration layer with pub/sub queues (Temporal, BullMQ, or AWS Step Functions) to manage long-running iterative agent loops, streaming telemetry, and token usage accounting.
Discussion
4 comments analyzed.
Concerns raised: Website copy full of vague AI-isms, Headline fails to communicate value proposition
Feature requests: Clarify website messaging and definitions
Competitors
Other products that read as similar to this one — 494 launches clear the similarity bar, closest 8 shown.
Attention rank: #272 of 495 (itself plus its competitors, highest first — normalized so YC and Product Hunt are compared fairly).
Launched 328 days after the earliest competitor.
- Gambit, an open-source agent harness for building reliable AI agents · hn · 2026-01-16 · 91 upvotes · similarity 0.52
- Ardent, a code-first agent for non-engineering work · hn · 2026-09-03 · 10 upvotes · similarity 0.52
- Agents, run any coding agent on your subscription not API costs · hn · 2026-05-31 · 6 upvotes · similarity 0.51
- Keen Code · hn · 2026-08-10 · 6 upvotes · similarity 0.51
- Multi-Agent Code Review · hn · 2025-11-04 · 5 upvotes · similarity 0.51
- You Are an Agent · hn · 2026-02-01 · 14 upvotes · similarity 0.50
- Prime Agent · ph · 2026-08-10 · 164 upvotes · similarity 0.49
- Mini-coder · hn · 2026-03-02 · 6 upvotes · similarity 0.48
Other launches for this product
- No other launches for this product.
Same idea, different domain
Nobody's really built a dev tools tool for Sales yet.