Search

More Filters

Show More
Add Listing
Go Back

humanlayer

0
New
Multi-Agent Platforms & Frameworks
Report

Report Abuse

Basic Information

HumanLayer is an open-source API and SDK that enables developers to embed deterministic human oversight into AI agents and tool-calling workflows. It provides Python and TypeScript/JavaScript packages, example integrations, and documentation so teams can bring their own LLMs and orchestration frameworks such as LangChain, CrewAI, and ControlFlow. The SDK makes it possible to pause or gate high-stakes function calls and contact humans for approvals, feedback, or advice across channels like Slack and Email. The repository includes examples, CLI tooling in beta, and a roadmap for additional channels and features. Its main purpose is to let agent developers safely grant agents access to external actions while ensuring a human is consulted before sensitive or high-impact operations are executed.

Links

Stars
1074
App URL
https://github.com/humanlayer/humanlayer
Github Repository
https://github.com/humanlayer/humanlayer/blob/main/README.md

Categorization

App Details

Features
The repo exposes a require_approval decorator that blocks specified function calls until a human approves and can pass denial feedback back to the LLM. It provides a human_as_tool primitive to invoke humans for advice, debugging, or collaboration. OmniChannel contact is supported for collecting human responses across Slack, Email and planned channels such as Discord and SMS. Granular routing lets teams target approvals to specific individuals or groups. The SDK is implemented at the tools layer so it supports bring-your-own LLM and major orchestration frameworks. The project includes framework-specific examples, CLI beta features, and a public roadmap showing planned integrations and alpha features.
Use Cases
HumanLayer helps teams make agentic automation safe by ensuring human oversight for medium and high-stakes actions that would otherwise be risky to automate. It prevents agents from performing sensitive writes or communicating on a user or company’s behalf without human approval, and feeds human feedback deterministically back to the LLM when calls are denied or modified. The SDK supports use in autonomous outer-loop agents by enabling durable workflows, scheduling primitives and integrations that allow agents to serialize and resume long-running tasks. It also helps with debugging and collaboration by giving agents a straightforward way to request human advice or approvals during tool execution.

Categories

Content Creation (5042)
Monetization & Business (2246)
Development Tools (1407)
Marketing & Social Media (1403)
Education & Career (1380)
Multi-Agent Platforms & Frameworks (1009)
Health & Life (957)
AI Resources (920)
Agents & Automation (778)
Data & Analytics (764)
Productivity Tools (679)
Writing & Editing (666)

Similar Listings

listing image

virtual lab

0 (0 review)
listing image

mnemo

0 (0 review)
listing image

EdgeChains

0 (0 review)
listing image

RAG Agents Accelerator

0 (0 review)
listing image

LLM Zero to Hundred

0 (0 review)

Featured Listings

Tags

Please fill the required fields*