Skip to main content
Early Access - Osmosis API is currently in early access. Contact us to get started!

​
Welcome to Osmosis API

Osmosis Agent Improvement API helps you build smarter, more context-aware AI agents. Our API provides essential building blocks for creating agents that learn from past interactions and make better decisions over time.

Quick Start

Get up and running with Osmosis API in minutes

API Reference

Explore our comprehensive API documentation

​
Key Features

Contextual Enhancement

Enrich your agent’s responses with relevant past knowledge using our powerful vector similarity search

Knowledge Storage

Store and learn from interaction histories with efficient data management

Continuous Learning

Improve agent responses based on past successes using our advanced learning algorithms

Smart Cleanup

Remove outdated or irrelevant knowledge automatically with intent-based deletion

​
Core Endpoints

The API provides three main endpoints to power your AI agents:
1

/enhance_task

Enhance an agent’s query with relevant knowledge from past interactions. Perfect for improving response quality and maintaining context.
POST https://osmosis.gulp.dev/enhance_task
2

/store_knowledge

Store conversation or event history for future reference. Builds your knowledge base over time.
POST https://osmosis.gulp.dev/store_knowledge
3

/delete_by_intent

Delete stale or irrelevant knowledge using intent matching. Keeps your knowledge base clean and relevant.
POST https://osmosis.gulp.dev/delete_by_intent
4

/knowledge_status/{job_id}

Check the status of a knowledge upload job. Monitor progress and handle completion.
GET https://osmosis.gulp.dev/knowledge_status/{job_id}

​
Why Use Osmosis?

AI Agent builders are often faced with the task of adding more and more edge case handling prompts to their agents. However, with osmosis it is now possible to attach those edge cases to the input prompt directly and keep the system prompts clean. We do this by using the enhance_task endpoint, which will attach edge cases learned from past interactions stored via the store_knowledge endpoint.
Here’s how Osmosis helps:
  • Vector-Based Storage: Efficiently store and retrieve interaction history
  • Semantic Search: Find relevant past experiences using advanced similarity matching
  • Structured Data: Maintain organized, queryable knowledge bases
  • Context Enrichment: Add relevant past knowledge to current queries
  • Pattern Recognition: Learn from successful interactions
  • Adaptive Responses: Improve output quality over time
  • Smart Cleanup: Automatically remove outdated information
  • Intent Matching: Delete irrelevant data based on semantic understanding
  • Data Freshness: Keep your knowledge base current and accurate

​
Getting Started

To start using the Osmosis API:
1

Get API Access

Contact us to request API access
2

Authentication Setup

Follow our authentication guide to set up your API key
3

Make Your First Call

Try our API endpoints with the provided examples

​
Need Help?

Email Support

Contact us at founders@gulp.ai

API Reference

Check our detailed API documentation
Ready to get started? Head over to our Quick Start guide to begin!