Osmosis

Osmosis (Gulp AI Inc.) is a forward-deployed reinforcement-learning platform for post-training large language models. Teams implement an AgentWorkflow and a Grader in Python, then use the Osmosis CLI and web platform to submit evaluation and training runs (GRPO/DAPO, multi-turn tool training) that produce task-specific LoRA models which beat foundation models at a fraction of the cost. Osmosis also ships an Agent Improvement REST API for storing agent interaction knowledge and enhancing agent tasks from past interactions, an open-source Python SDK/CLI (osmosis-ai), a TypeScript logging SDK, an open-source MCP server (Osmosis-Apply), webhooks, and hosted documentation. Backed by CRV, Felicis, and Paradigm.

Osmosis publishes 3 APIs on the APIs.io network: agent API, knowledge API, and Osmosis Agent Improvement API API. Tagged areas include Company, AI, Reinforcement Learning, LLM, and Post-Training.

The Osmosis catalog on APIs.io includes 1 event-driven AsyncAPI specification.

Osmosis’ developer surface includes documentation, API reference, getting-started guide, engineering blog, support, signup flow, CLI, and 22 more developer resources.

🌐 Visit website 📡 Source on GitHub
54.7/100 developing ▬ flat Agent 75/100 agent native Full breakdown ↓
scored 2026-07-27 · rubric v0.5
AccessSelf serve
3 APIs 1 MCP Servers
CompanyAIReinforcement LearningLLMPost-TrainingModel TrainingAgentsMachine LearningDeveloper Tools

Kin Score

Kin Score Kin Score How this is scored →
scored 2026-07-27 · rubric v0.5
Composite quality — 54.7/100 · developing
Contract Quality 16.5 / 25
Developer Ergonomics 16.1 / 20
Commercial Clarity 8.4 / 20
Operational Transparency 3.8 / 13
Governance 0.0 / 12
Discoverability 10.0 / 10
Agent readiness — 75/100 · agent native
Machine-Readable Contract 18 / 18
Agentic Access Contract 15 / 15
MCP Server 12 / 12
Machine-Readable Auth 10 / 10
Idempotency 0 / 9
Stable Error Semantics 8 / 8
Request/Response Examples 0 / 7
Rate-Limit Signaling 0 / 7
Typed Event Surface 6 / 6
Agent Skills 5 / 5
Well-Known Catalog 4 / 4
Consent & Bot Identity 0 / 3
Improve this rating by publishing the missing artifacts — every area above can be raised, and the full rubric is at apis.io/rating/. This rating is computed from github.com/api-evangelist/osmosis: open an issue to ask a question, or submit a pull request to add artifacts. Want it done for you? Prioritized profiling — $2,500 →

APIs 3

Individual APIs this provider publishes, each with its own machine-readable definition.

Osmosis agent API

Operations for enhancing agent interactions and decisions

Osmosis knowledge API

Operations for managing the knowledge base

Osmosis Osmosis Agent Improvement API API

The Osmosis Agent Improvement API API from Osmosis — 1 operation(s) for osmosis agent improvement api.

MCP Servers 1

Model Context Protocol servers that expose these APIs to AI agents.

osmosis-mcp.yml

MCP SERVER

Event Specifications 1

AsyncAPI definitions for this provider's event-driven and streaming APIs.

Osmosis Webhooks

ASYNCAPI

Security Posture 2

Authentication, domain security, vulnerability disclosure, and trust-center signals.

Osmosis Authentication

apiKey · 1 scheme

SECURITY

Osmosis Domain Security

TLSv1.3 · HSTS · DNSSEC · DMARC

SECURITY

Agentic Access 1

Recommended x-agentic-access execution contracts for AI agents.

Osmosis Agentic Access

5 operations · 3 acting

5 operations · 3 acting

AGENTIC

Resources

Get Started 3

Portal, sign-up, and the first successful call

DeveloperPortal
DeveloperPortal
 GettingStarted
GettingStarted
 SignUp
SignUp

Documentation 2

Reference material describing how the API behaves

Documentation
Documentation
 APIReference
APIReference

Agent Surfaces 5

MCP servers, agent skills, and machine-readable catalogs

MCPServer
MCPServer
 LLMsTxt
LLMsTxt
 WellKnown
WellKnown
 AgentSkill
AgentSkill
 AgenticAccess
AgenticAccess

Design & Contract 6

Pagination, idempotency, versioning, errors, and events

Conformance
Conformance
 ErrorCatalog
ErrorCatalog
 Lifecycle
Lifecycle
 Conventions
Conventions
 DataModel
DataModel
 Webhooks
Webhooks

Build 4

SDKs, sample code, and the tooling you integrate with

GitHubOrganization
GitHubOrganization
 Packages
Packages
 SDKs
SDKs
 CLI
CLI

Access & Security 3

Authentication, authorization, and security posture

TrustCenter
TrustCenter
 DomainSecurity
DomainSecurity
 Authentication
Authentication

Operate 2

Status, limits, changes, and where to get help

Support
Support
 ChangeLog
ChangeLog

Commercial 2

Pricing, plans, and the legal terms of use

TermsOfService
TermsOfService
 PrivacyPolicy
PrivacyPolicy

Company 2

The organization behind the API

Website
Website
 Blog
Blog

Source (apis.yml)

apis.yml Raw ↑ 
aid: osmosis
name: Osmosis
description: Osmosis (Gulp AI Inc.) is a forward-deployed reinforcement-learning platform for post-training large language
  models. Teams implement an AgentWorkflow and a Grader in Python, then use the Osmosis CLI and web platform to submit evaluation
  and training runs (GRPO/DAPO, multi-turn tool training) that produce task-specific LoRA models which beat foundation models
  at a fraction of the cost. Osmosis also ships an Agent Improvement REST API for storing agent interaction knowledge and
  enhancing agent tasks from past interactions, an open-source Python SDK/CLI (osmosis-ai), a TypeScript logging SDK, an open-source
  MCP server (Osmosis-Apply), webhooks, and hosted documentation. Backed by CRV, Felicis, and Paradigm.
url: https://raw.githubusercontent.com/api-evangelist/osmosis/refs/heads/main/apis.yml
accessModel:
  pricing: unknown
  onboarding: self-serve
  trial: false
  try_now: false
  public: false
  label: Self-serve signup
  confidence: medium
  source:
  - authentication
  generated: '2026-07-22'
  method: derived
image: https://raw.githubusercontent.com/Osmosis-AI/osmosis-sdk-python/main/.github/osmosis-logo-light.svg
x-type: company
x-source: vc-portfolio
x-backed-by:
- crv
- felicis
- paradigm
x-tier: stub
x-tier-reason: portfolio-lead
x-legal-entity: Gulp AI Inc.
specificationVersion: '0.20'
created: '2026-07-17'
modified: '2026-07-20'
x-enrichment:
  date: '2026-07-20'
  status: enriched
  artifacts_added: 20
  pass: local-v1
tags:
- Company
- AI
- Reinforcement Learning
- LLM
- Post-Training
- Model Training
- Agents
- Machine Learning
- Developer Tools
apis:
- aid: osmosis:osmosis-agent-api
  name: Osmosis agent API
  description: Operations for enhancing agent interactions and decisions
  humanURL: https://docs.osmosis.ai
  baseURL: https://api.osmosis.ai
  tags:
  - agent
  properties:
  - type: OpenAPI
    url: openapi/osmosis-agent-api-openapi.yml
- aid: osmosis:osmosis-knowledge-api
  name: Osmosis knowledge API
  description: Operations for managing the knowledge base
  humanURL: https://docs.osmosis.ai
  baseURL: https://api.osmosis.ai
  tags:
  - knowledge
  properties:
  - type: OpenAPI
    url: openapi/osmosis-knowledge-api-openapi.yml
- aid: osmosis:osmosis-osmosis-agent-improvement-api-api
  name: Osmosis Osmosis Agent Improvement API API
  description: The Osmosis Agent Improvement API API from Osmosis — 1 operation(s) for osmosis agent improvement api.
  humanURL: https://docs.osmosis.ai
  baseURL: https://api.osmosis.ai
  tags:
  - Osmosis Agent Improvement API
  properties:
  - type: OpenAPI
    url: openapi/osmosis-osmosis-agent-improvement-api-api-openapi.yml
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com
- FN: APIs.json
  email: info@apis.io
common:
- type: Website
  url: https://osmosis.ai/
- type: DeveloperPortal
  url: https://docs.osmosis.ai
- type: Documentation
  url: https://docs.osmosis.ai
- type: APIReference
  url: https://docs.osmosis.ai/openapi.json
- type: GettingStarted
  url: https://docs.osmosis.ai/platform/quickstart
- type: Blog
  url: https://osmosis.ai/blog
- type: Support
  url: https://osmosis.ai/contact
- type: GitHubOrganization
  url: https://github.com/Osmosis-AI
- type: SignUp
  url: https://platform.osmosis.ai
- type: TermsOfService
  url: https://osmosis.ai/legal/terms
- type: PrivacyPolicy
  url: https://osmosis.ai/legal/privacy
- type: TrustCenter
  url: https://trust.osmosis.ai
- type: Packages
  url: packages/osmosis-packages.yml
- type: SDKs
  url: packages/osmosis-packages.yml
- type: CLI
  url: cli/osmosis-cli.yml
- type: MCPServer
  url: mcp/osmosis-mcp.yml
- type: LLMsTxt
  url: llms/osmosis-llms.txt
- type: WellKnown
  url: well-known/osmosis-well-known.yml
- type: Conformance
  url: conformance/osmosis-conformance.yml
- type: ErrorCatalog
  url: errors/osmosis-problem-types.yml
- type: Lifecycle
  url: lifecycle/osmosis-lifecycle.yml
- type: ChangeLog
  url: changelog/osmosis-changelog.yml
- type: Conventions
  url: conventions/osmosis-conventions.yml
- type: DataModel
  url: data-model/osmosis-data-model.yml
- type: Webhooks
  url: asyncapi/osmosis-webhooks.yml
- type: AgentSkill
  url: skills/_index.yml
- type: DomainSecurity
  url: security/osmosis-domain-security.yml
- type: AgenticAccess
  url: agentic-access/osmosis-agentic-access.yml
- type: Authentication
  url: authentication/osmosis-authentication.yml