HN Showcase
Back to browse
Calljmp–TypeScript agentic back end+runtime for production AI workflows

Calljmp–TypeScript agentic back end+runtime for production AI workflows

by HannaCh_5·Feb 25, 2026·2 points·0 comments
Visit ProjectView on HN

AI Analysis

●●SolidSolve My ProblemShip It

TypeScript agent runtime with HITL and cost tracking, but crowded against Replicate, Modal, and LangGraph Cloud.

Strengths
  • •Thoughtful split-of-concerns: you own business logic/UI, platform owns state/retries/observability — clear mental model.
  • •Persistent state and pause/resume for long-running workflows is genuinely useful for agentic patterns that existing serverless platforms don't prioritize.
  • •Cost tracking + trace observability bundled in, reducing operational friction compared to wiring together LangSmith + custom logging.
Weaknesses
  • •Agentic workflow platforms are crowded (Replicate, Modal, LangGraph Cloud, Temporal)—no clear differentiation in the pitch beyond 'TypeScript + HITL.'
  • •Live preview and landing page work, but no public code examples, pricing, or SLA details—hard to evaluate production-readiness claims.
Target Audience

Backend developers and AI/full-stack engineers building production AI agents and copilots

Similar To

Modal · Replicate · LangGraph Cloud

Post Description

We built Calljmp — a managed backend/runtime for agent-like workflows written in TypeScript.

It focuses on: – persistent state and long-running executions – retries, branching and pause/resume – observability (logs, traces, cost) – human-in-the-loop approvals

Launched on DevHunt: https://devhunt.org/tool/calljmp

Happy to hear feedback or questions from the HN community.

Similar Projects

AI/ML●●Solid

We made a back end agnostic SDK for Agent Memory

Backend-agnostic memory SDK with local embeddings and benchmark claims on BEAM.

Big BrainShip It
ethanjoffe
5429d ago
Developer Tools●●Solid

Production-Ready NestJS Back End (Multi-Tenancy, Event-Driven)

Concrete, hands-on demos — row-level multi-tenancy implemented with Prisma, async jobs via BullMQ/Redis, and tracing through OpenTelemetry/Jaeger — make this a useful reference for people building SaaS backends. It’s not reinventing the stack, but the repo bundles several production patterns and infra pieces together in a way that’s easy to explore; would be stronger with architecture diagrams, runnable quickstart scripts and example data.

Niche GemShip It
PkLavc
104mo ago