inferablehq

inferable

TypeScript2024–2025

inferablehq / inferable

inferable

Build reliable AI Workflows and Agents with humans in the loop, structured outputs and durable execution.

AI & Machine Learning Web Development Automation & Workflows

Explore on GitHub Read Hacker News discussions

2Distinct people

8Mentions

0Explicit recommenders

450GitHub stars

REPOSITORY AT A GLANCE

What to know before exploring

What it is

Build reliable AI Workflows and Agents with humans in the loop, structured outputs and durable execution.

GitHub

Where it is used

No documented product use has been verified yet.

What people are saying

No recommendation phrase was found in the indexed comments.

No classified warning is attached to this page. Read the discussions before treating silence as approval.

Also in these discussions

No other repository is repeatedly linked in the same discussions.

This week on Hacker News

Nov 7–Nov 14 UTC · Direct repository links and separately labeled related project stories. Indexed through 11/14/2026, 3:56:07 PM UTC.

No direct repository links were found in the indexed HN discussions over the past seven days. Older discussions are available below.

Mentions over time

HN mentions by week8 dated mentions

Observed mentions: 2024-12-05 23:00:20 UTC to 2025-02-06 21:32:27 UTC. Weeks start Monday, UTC.

Counts come from the repository’s dated source evidence. Index cutoff: 2026-11-02 08:16:59 UTC.

View mention counts and date ranges

UTC ranges include their start and exclude their end. Select a period to filter the source evidence.
Period	Start (UTC)	End (exclusive, UTC)	Mentions	Submissions	Comments
Dec 2	2024-12-02 00:00:00 UTC	2024-12-09 00:00:00 UTC	1	1	0
Dec 9	2024-12-09 00:00:00 UTC	2024-12-16 00:00:00 UTC	0	0	0
Dec 16	2024-12-16 00:00:00 UTC	2024-12-23 00:00:00 UTC	0	0	0
Dec 23	2024-12-23 00:00:00 UTC	2024-12-30 00:00:00 UTC	0	0	0
Dec 30	2024-12-30 00:00:00 UTC	2025-01-06 00:00:00 UTC	1	0	1
Jan 6	2025-01-06 00:00:00 UTC	2025-01-13 00:00:00 UTC	1	0	1
Jan 13	2025-01-13 00:00:00 UTC	2025-01-20 00:00:00 UTC	1	0	1
Jan 20	2025-01-20 00:00:00 UTC	2025-01-27 00:00:00 UTC	2	1	1
Jan 27	2025-01-27 00:00:00 UTC	2025-02-03 00:00:00 UTC	1	1	0
Feb 3	2025-02-03 00:00:00 UTC	2025-02-10 00:00:00 UTC	1	1	0

What Hacker News says

8 sources

johnjcsmith·Feb 6, 2025Submission

Show HN: Inferable – Build Reliable AI Agents with Durable Execution

Hey HN, We've been trying to make agents "programmatically useful" and built an open-source AI-native workflow orchestrator called Inferable. We integrate Tools, Agents, and Durable Workflows in a code-first way to create "Durable Agentic Workflows". Basically: 1. We provide SDKs to wrap your existing code as tools. 2. Our agent abstraction dynamically searches through all the tools, and calls them in a multi-step reasoning process. 3. Durable workflows help you string together agent interactions using "workflow as code". The control plane handles the orchestration of the workflow and the agents, and we've done some things to failover on machine stalls, tool failures, and other disasters. We also use long-polling, so workflows and tools don't need any network ingress. There's a lot more to it, but we're seeking any early feedback you have

Read the rest

4 points · Open discussion

johnjcsmith·Jan 29, 2025Submission

Show HN: Pgchat – One command to chat with any Postgres database

Hey HN, Sharing a project we have been working on which provides an LLM-powered chat experience for querying Postgres databases (local or remote). pgchat takes a Postgres connection string and spawns a terminal UI for the chat: `npx pgchat postgresql://xxxx` It is built on top of our other project Inferable [1] which handles the LLM requests (open source / self hostable). Database queries are issued from the pgchat process to the connection string which allows for use with local Postgres instances. Keen to hear your thoughts! [1] https://github.com/inferablehq/inferable

3 points · Open discussion

lunarcave·Jan 22, 2025

Does this [1] look like the thing you're looking for? We built a basic Re-Act agent that can dynamically inspect the database context and generate the queries iteratively. Our experience was that it was hard to do single-shot. Happy to answer any questions. [1] https://github.com/inferablehq/inferable/tree/main/adapters/...

In Ask HN: Integrating SQL and LLM what is you experience

lunarcave·Jan 20, 2025Submission

Show HN: Open-source conversational AI agents for internal tools

Hey HN, We're John and Nadeesha. We created Inferable. [1] After years of working in operationally-intensive startups, we got tired of watching our internal tools gather dust and break. We've all been there - you build a tool, it works great for a while, then the API changes and suddenly you're back to square one. Sure, Retool and similar tools help, but someone still has to maintain them, and the backlog of "quick fixes" and the mountain of glue code keeps keeps growing. We started Inferable to see whether LLMs can help here. Inferable helps developers create conversational AI agents that act as the orchestration layer between existing internal APIs and human intent. Instead of building custom scripts or internal tools, developers can quickly set up these agents as conversational experiences [2]. We natively integrate with Slack and emai

Read the rest

l (more coming), while also supporting Zapier and HTTP APIs for more advanced workflows. Our SDKs can wrap existing functions, or existing APIs (REST, GraphQL). We use long polling for message delivery, which means these instances don’t have to open ports / configure network ingress. A Re-Act agent dynamically searches through these tools based on user context, schedules jobs as tool calls, and iterates based on the result. We prioritize using existing codebases as deterministic guardrails. For additional verifications, we provide primitives to easily implement human-in-the-loop processes, custom authn, and authz, all backed with your existing codebases. Our customers use Inferable to: - Interact conversationally with internal APIs and databases (with restricted connections) - Programmatically process Datadog alerts - automatically tagging them and routing them with enriched context - Programatically or conversationally enrich Zendesk support tickets by automatically adding context from multiple internal systems To achieve this functionality, we've developed: - A built-in Re-Act (reasoning + action) agent - A distributed job queue for managing long-running tasks - End to end chat state, and message serialisation for tool calls - Service discovery and function registry for tools - Context-aware dynamic tool search - Native SDKs for Node.js, Golang, C#, and other languages We’re open-source (MIT) and fully self-hostable within existing infrastructure. Happy to receive any feedback or answer questions. --- [1] https://github.com/inferablehq/inferable [2] Acknowledging that calling an LLM every time is costlier than using a script, we’re solving the problem of repeating these flows without LLM intervention in our next iteration.

11 points · Open discussion

lunarcave·Jan 14, 2025

The discourse, has been taken over by hype - I'll give you that. I'm in the space [1] and I'll try my best to answer. Building on your definition, I'd say an agent is is a collection of LLM calls with structured outputs. You can give an LLM some context and ask "what's the next step?". And agent does that recursively, with some exit condition. Those structured outputs inform the control flow of the agent, so much so that at the end of the execution, you can argue that the agent has "written its own control flow". The structured outputs may produce: - Function calls, and their inputs (tool calling) - Some reasoning text (for the context) - An exit condition evaluation (done=true) Hope that helps! [1] https://github.com/inferablehq/inferable

In Ask HN: Is "agent" just a fancier term for "LLM with structured output"?

lunarcave·Jan 7, 2025

Doing something open-source [1] in the space. Self-hostable as well. Our customers actually have built internal things to help them with Zendesk / replace some manual Retool tasks. There's a slack [2] integration as well. Fun fact, we use it to query our Zendesk / Postgres / Auth system from Slack and avoid internal tools. E-mail in the profile. Happy to chat, even if it's to recommend something that works better for your use case. [1] https://github.com/inferablehq/inferable [2] https://docs.inferable.ai/pages/slack

In Ask HN: Open-source AI Agents building platform?

lunarcave·Jan 3, 2025

Yes! I've worked on something [1] in the space lately, and can share learnings. It generates queries, which gets fed to the application layer, and it executes them based on some deterministic controls. Basically, if you're working with a database that has some actually useful/critical data, put an application layer in the middle that can gatekeep LLM access. - Depending on your risk appetite, make a decision on providing a read-only URL to the thing that interfaces with the LLM. - For maximum control over the queries, you can wrap then in functions (tools) and let the LLM only call the tools. But this takes away a lot of the power. What we've basically done is allowing the LLM to read the context progressively [2] and give it free reign over the queries. - The said application layer can ask for approval on all of the queries. (Human in th

Read the rest

e loop). [3] - (Optionally) If your query returns a lot of data, putting all of that through the LLM context might be expensive. You need a way to return data out of band from a query, directly to the user. [1] https://github.com/inferablehq/inferable/tree/main/data-conn... [2] https://github.com/inferablehq/inferable/blob/ec504b8593f41b... [3] https://github.com/inferablehq/inferable/tree/main/data-conn...

In Ask HN: How to Safeguard a LLM to SQL Prompt from SQL Injection?

johnjcsmith·Dec 5, 2024Submission

Show HN: Data Connector – Chat with Your Database and APIs

Hey HN! Wanted to share a project I have been working. Data Connector is an open source tool for interacting with Databases (Postgres, MySQL, SQLite) using natural language. Prompts are handled using a ReAct[1] agent which has access to the schema and a tool for executing queries. It also has experimental[2] support for calling APIs (OpenAPI, GraphQL) which allows for queries that can span multiple systems (Find this user's details in Clerk, etc). We have mostly been using it for managing our local development environment, but it has configurable controls for running in other environments. - Privacy Mode which never sends query results back to the LLM context, instead the result is returned to the user as JSON - Approval Mode which requires manual approval of each query before it is executed Data Connector runs within a private subnet, co

Read the rest

nnects to the database and polls for new queries. There is no requirement to open traffic to the database or share credentials / connection strings. Data Connector is built using another project we are working on Inferable (also open source) which is a runtime for building and observing LLM-based agents. Would love your thoughts! [1] https://arxiv.org/abs/2210.03629 [2] We have been testing these with various schemas and are currently working on better handling for large OpenAPI specs, etc.

17 points · Open discussion