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 API contracts indexed on the APIs.io network: Agent API, Knowledge API, and Agent Improvement API. Tagged areas include Company, Artificial Intelligence, Reinforcement Learning, LLM, and Post-Training.

The Osmosis catalog on APIs.io includes 1 event-driven AsyncAPI specification and 1 Spectral governance ruleset.

Osmosis’ developer surface includes documentation, API reference, getting-started guide, engineering blog, support, signup flow, CLI, and 24 more developer resources.

🌐 Visit website 📡 Profile data on GitHub

46.2/100 developing ▬ flat Agent 36/100 agent ready Front door AI 5/6 prominent Heartbeat 61/100 alive saas Full breakdown ↓
scored 2026-11-06 · rubric v0.27.0 · Show this score on your site →

1 published contract 1 MCP Servers 2 Agent Skills

Company Artificial Intelligence Reinforcement Learning LLMPost-TrainingModel Training Agents Machine Learning Developer Tools

What this lets a business do 1

Business capabilities this provider's published APIs can perform, derived from its own contracts. Browse all capabilities →

Information & Data Management

BC-610

Agent

POST /enhance_task

Kin Score

Kin Score How this is scored →
scored 2026-11-06 · rubric v0.27.0

Composite quality — 46.2/100 · developing

Contract Quality 10.6 / 19

Developer Ergonomics 11.0 / 15

Access Clarity 3.2 / 15

Operational Transparency 2.6 / 10

Contract Governance 1.6 / 9

Discoverability 5.4 / 8

Regulatory Posture 3.4 / 15

Create-or-Update Ergonomics 0.0 / 10

Agent readiness — 36/100 · agent ready

Machine-Readable Contract 18 / 18

Agentic Access Contract 10 / 10

Documented Reversibility 0 / 6

MCP Server 12 / 12

Machine-Readable Auth 10 / 10

Idempotency 0 / 9

Stable Error Semantics 8 / 8

Request/Response Examples 7 / 7

Rate-Limit Signaling 0 / 7

Typed Event Surface 6 / 6

Agent Skills 5 / 5

Well-Known Catalog 0 / 4

Consent & Bot Identity 0 / 3

A2A Agent Card 0 / 8

Dry-Run / Simulate Mode 0 / 4

Delegated User Identity 0 / 6

Protected Resource Metadata 0 / 5

Registration Without a Human 0 / 6

Agentic Commerce Well-Known Document 0 / 5

Pagination 5 / 5

Distinct Operations 3 / 3

MCP Tool Quality 6 / 6

Regulatory Posture applies to this provider. Its tags matched the Horizontal (data, software, accessibility, platform) regime, so Regulatory Posture carries 15 points of the composite. If this regime is wrong for your business, say so on your provider repo — the applicability map is public and we will correct it.

Create-or-Update Ergonomics applies to this provider. This API accepts writes, so it carries 10 points of the composite. It is scored from the published contracts themselves: whether a caller can create-or-update in one call, whether the write accepts a key the caller already holds, and whether the response says which branch ran. Without that, every write needs a search-and-branch in front of it, and the first time that check is skipped a duplicate record is created. Scored against the observed mean rather than raw — a provider at the catalog average is unchanged by this facet, not penalised by it.

The six quality facets above are damped to 75 points between them, because the conditional facet above carries the other 25. That is why each facet's contribution is shown against a damped maximum: raising a quality facet moves the composite by 75% of its nominal weight, not 100%. The full arithmetic is at apis.io/rating/.

Show this score on your site.

It updates itself when the score changes. Paste this where you link to your API docs:

<a href="https://apis.io/providers/osmosis/"><img src="https://apis.io/badge/osmosis/card.svg" alt="Osmosis on APIs.io — Kin Score by API Evangelist"></a>

Other styles, a README pill and a shields.io endpoint are on the badge page.

Raise your score.

Agent readiness — checks not met, largest first (exact, from this profile):

Idempotency +9 pts — OpenAPI mutating operations declare an idempotency key — a header, a request-body property, or a named de-duplication token whose own description says so (verified); else common[].type matches /idempoten/i (documented)
A2A Agent Card +8 pts — a2a/-a2a.yml manifest, graded on conformance.grade against A2A 1.0.0
Rate-Limit Signaling +7 pts — OpenAPI responses document X-RateLimit-* / RateLimit headers (verified), else a rate_limits artifact or RateLimits link (documented)
Registration Without a Human +6 pts — a `registration_endpoint` in the served RFC 8414 / OIDC discovery document
Delegated User Identity +6 pts — a served discovery document listing authorization_code in grant_types_supported (served), else an oauth2 authorizationCode flow or openIdConnect declared in an OpenAPI (documented)
Documented Reversibility +6 pts — a reversal operation in the contract, graded up when a window is documented too

5 more unmet checks in the Agent Readiness table above.

Kin Score — facets with the most composite points still available (weight × headroom):

Access Clarity scores 21.1 — up to +15.8 composite points
Contract Quality scores 56.7 — up to +10.8 composite points
Contract Governance scores 18.2 — up to +9.8 composite points

Each check links to what satisfies it. Publish the artifact, or tell us where it already lives, and the score moves on the next scoring run.

Improve this rating by publishing the missing artifacts — every area above can be raised, and the full rubric is at apis.io/rating/. Every facet and dimension name above is a link: it opens that measurement's own page — what it means, the exact checks that feed it, how the whole catalog distributes on it, and the providers at the top of it. This rating is computed from the provider profile at artifacts.apis.io/osmosis/apis.yml: open an issue on github.com/api-evangelist/osmosis to ask a question or point us at an artifact you publish. Submit an artifact on GitHub — free → Manage your own listing — the Influence plan, $499/mo →

Markets this provider is in provisional

The Kin Score Market layer reads a provider inside its market: its position, and how deep its integrations go. Depth is only comparable within a position. Provisional and unweighted: not part of the Kin Score or agent readiness.

Market	Position	Depth	Registered MCP server	Declares compatibility
Hugging Face Hub Organisations	builds-on	26.8 (thin)	-	-

Registered MCP server and declares compatibility are report only — not weighted. Undeclared means we found nothing we can read, so there is no number: we never infer integrations.

Standards implemented 2

Standards this provider implements or carries. De facto ones are profiled and measured by the API Commons; formal ones come from the standards directory and are linked by the provider's own tags. The evidence column says how each claim was established — not that it was made.

Model Context Protocol (MCP)

measured — observed by APIs.io (documented)

OpenAPI

measured — observed by APIs.io (published)

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 Agent Improvement API

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

Open Collections 3

Open, tool-agnostic API collections (OpenAPI-derived and Bruno).

Osmosis Improvement agent API

OPEN COLLECTION

Osmosis Improvement agent knowledge API

OPEN COLLECTION

Osmosis Improvement agent Osmosis Agent Improvement API API

OPEN COLLECTION

MCP Servers 1

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

Osmosis MCP Server

An open-source Model Context Protocol server that uses the Osmosis-Apply-1.7B model (served locally via Ollama) to merge code edits into files. Integrates into AI IDE / MCP-clie...

MCP SERVER

Agent Skills 2

Packaged agent skills for driving this provider's APIs from an AI assistant.

Enhance an agent task with Osmosis memory

AGENT SKILL

Store and manage agent interaction knowledge

AGENT SKILL

Event Specifications 1

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

Osmosis Webhooks

ASYNCAPI

Spectral Rules 1

Spectral governance rulesets for linting and validating these APIs.

Osmosis API Rules

47 rules · 45 errors 1 warnings 1 info

SPECTRAL

OpenAPI Overlays 1

Overlays applied on top of this provider's contracts. Each card says who wrote it: a document the provider publishes, or one API Evangelist derived or generated.

Osmosis Agent Improvement Overlay

4 actions · update · osmosis-agent-improvement-openapi.json

DERIVED

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

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

LLMsTxt

WellKnown

AgentSkill

AgenticAccess

Design & Contract 6

Pagination, idempotency, versioning, errors, and events

Conformance

ErrorCatalog

Lifecycle

Conventions

DataModel

Webhooks

Build 4

SDKs, sample code, and the tooling you integrate with

GitHubOrganization

Packages

SDKs

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

Other 2

Properties that don't map to a standard resource type

CapabilityMap

CapabilityMap

Overlay

Overlay

Source (apis.yml)

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
deliveryModel:
  model: saas
  open_source: false
  commercial: true
  callable_host: true
  label: Hosted service · you call their endpoint
  confidence: high
  source:
  - openapi
  - pricing
  generated: '2026-08-28'
  method: derived
accessModel:
  pricing: unknown
  onboarding: unknown
  trial: false
  try_now: false
  public: false
  label: Unknown
  confidence: low
  source:
  - authentication
  - security
  generated: '2026-11-06'
  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: '0.23'
created: '2026-07-17'
modified: '2026-09-16'
x-docs-platform: mintlify
x-docs-platform-confidence: medium
x-docs-platform-checked: 2026-10-04
x-enrichment:
  date: '2026-07-20'
  status: enriched
  artifacts_added: 20
  pass: local-v1
tags:
- Company
- Artificial Intelligence
- Reinforcement Learning
- LLM
- Post-Training
- Model Training
- Agents
- Machine Learning
- Developer Tools
tags_raw:
- Company
- AI
- Reinforcement Learning
- LLM
- Post-Training
- Model Training
- Agents
- Machine Learning
- Developer Tools
- Machine-Learning
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:
  - Agents
  tags_raw:
  - 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
  tags_raw:
  - knowledge
  properties:
  - type: OpenAPI
    url: openapi/osmosis-knowledge-api-openapi.yml
- aid: osmosis:osmosis-osmosis-agent-improvement-api-api
  name: Osmosis Agent Improvement 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: CapabilityMap
  url: capabilities/osmosis-capability-edges.yml
  name: Osmosis Business Capability Map
- type: Overlay
  url: overlays/osmosis-agent-improvement-overlay.yaml
- 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

Osmosis API — frequently asked questions

Does Osmosis have an API?

Yes. APIs.io lists 3 APIs from Osmosis, including Osmosis Agent API, Osmosis Knowledge API and Osmosis Agent Improvement API.

Is there an OpenAPI specification for the Osmosis API?

Yes. APIs.io indexes 3 OpenAPI specifications for Osmosis, each linked for download from this page.

How do I authenticate with the Osmosis API?

Osmosis uses bearer-token authentication (apiKey · 1 scheme). The details are profiled on APIs.io as Osmosis Authentication.

Does Osmosis have an MCP server?

Yes. APIs.io lists 1 MCP server for Osmosis: An open-source Model Context Protocol server that uses the Osmosis-Apply-1.7B model (served locally via Ollama) to merge code edits into files. Integrates into AI IDE / MCP-client workflows. Requires

Is the Osmosis API ready for AI agents?

Osmosis has a Kin Score of 46.2 out of 100 (developing) and an Agent Readiness score of 35.6 (agent-ready), scored by API Evangelist on 2026-11-06.

Work with this as data

Every provider here is available over the APIs.io API and to AI agents over MCP.

MCP server

One button, every client — Claude, Cursor, VS Code and the rest.

https://apis.io/mcp

Tools for providers

9 MCP tools reach this

find_providersBrowse and filter every provider in the catalog.
get_provider_artifactsEvery artifact this provider publishes, grouped by type.
get_provider_operationsEvery operation across all of their OpenAPIs — one call instead of parsing every spec.
get_provider_toolsEvery MCP tool they ship, with the operation each wraps.
get_provider_evidenceHow each part of their score was established. Free — the basis for a claim should not sit behind it.
get_provider_ratingPRO — composite, band, trend and facet scores.
apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.
resolveTurn a domain, URL or GitHub org into the provider it belongs to.
find_cohortsEvery scored population of providers in the catalog.

All 92 tools →

Call it yourself

curl for this page

This provider

curl "https://apis.io/api/v1/providers/osmosis"

All providers

curl "https://apis.io/api/v1/providers?limit=25"

Every operation they expose

curl "https://apis.io/api/v1/providers/osmosis/operations?limit=25"

How their score was established

curl "https://apis.io/api/v1/providers/osmosis/evidence"

Calls without X-API-Key need no key. Calls with it need a paid plan — get a key.

Get an API key

Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.

GitHub Google LinkedIn

A second provider on the same verified email joins the account you already have.