Skip to content
entertao
Menu

Bittensor services for AI agents

Enter the network of intelligence.

Inference, compute, search and data from Bittensor subnets, in one place. Find the right service, see exactly what access it needs, and let your agent call the provider directly with x402, Gamma or your own API key.

Most integration-ready

Ranked by checks, documented access and documentation. No usage data.

How we rank
  1. 1
    blockmachine

    Live execution tested · Direct call documented · 1 operation with known parameters

    SN1913
  2. 2
    Decision Models

    Direct call documented · 5 operations with known parameters · 2 supported access methods

    SN9210
  3. 3
    Lium

    Direct call documented · 40 operations with known parameters · 2 supported access methods

    SN5110
  4. 4
    Attelier

    Direct call documented · 12 operations with known parameters · 1 supported access method

    SN1269
  5. 5
    Cathedral

    Direct call documented · 36 operations with known parameters · 1 supported access method

    SN949
  6. 6
    Chutes

    Direct call documented · 40 operations with known parameters · 1 supported access method

    SN649
  7. 7
    Desearch

    Direct call documented · 40 operations with known parameters · 1 supported access method

    SN229
  8. 8
    Ephemeris

    Direct call documented · 2 operations with known parameters · 1 supported access method

    SN919
Indexed subnets
129
active on finney
Available products
88
researched from subnet sites
API endpoints
3,307
from validated OpenAPI specs
Verified services
18
API answers + valid spec
MCP services
14
publish an MCP server

Chain sync 20 Nov 2026, 20:33 UTC · block 9,550,234 · 8 on-chain service records. Counts come from the live registry; no usage or payment volumes are tracked.

Connect

Connect your AI agent

Add the hosted MCP with one URL, or point any agent at /SKILL.md. No installation, no account; your agent then calls the provider directly.

Hosted MCP · one URL, nothing to install

Read-only

Claude Code

claude mcp add --transport http entertao https://entertao.com/mcp

Any other MCP client (Streamable HTTP)

https://entertao.com/mcp

Any agent that reads URLs

Read https://entertao.com/SKILL.md and use it to find a Bittensor service for my task.
  • Service search in plain words
  • API docs and endpoints
  • Access manifests
  • Sign-up and payment methods
  • Does not call providers
  • Never takes keys, wallets or payments

Your agent then calls the provider directly with its own tools and your own access (API key, gamma deposit or x402 wallet). How it works

Explore

Service explorer

88 products from 129 subnets. Filters combine; payment filters show one method at a time.
  1. Chutes
    SN64 · chutes.ai
    Verified

    Serverless inference for open-source AI models, plus deployment of custom models on rented GPUs

    API KeyAPI verified
  2. Reliquary
    SN81 · reliqua.ai
    Verified

    Decentralized post-training platform for batch generation, model evaluations and planned RL training on distributed GPUs

    API KeyGamma· subnetAPI verified
  3. Actual
    SN95 · actual.inc
    Reachable

    Runs open-source models on your own Mac, Windows or Linux machines behind one private API reachable through a relay

    FreeAPI KeyEndpoint reachable
  4. engy
    SN53 · engy.ai
    Reachable

    Inference API for open-source models served on a GPU network, compatible with OpenAI and Anthropic clients

    API KeyGammaEndpoint reachable
  5. Fugal
    SN70 · fugalai.com
    Reachable

    LLM router that picks one model per question by price and quality, available as chat and an API in OpenAI and Anthropic formats

    FreeAPI KeyEndpoint reachable
  6. SayGM
    SN28 · saygm.com
    Reachable

    LLM gateway for Claude, GPT, Gemini and open models with OpenAI, Anthropic and Gemini API formats and private TEE inference

    API KeyGamma· subnetEndpoint reachable
  7. Terza Inference
    SN103 · terza.si
    Reachable

    Model API routing requests to miner-served models, with OpenAI- and Anthropic-style endpoints and billing on verified usage

    API KeyGamma· subnetEndpoint reachable
  8. Yugos
    SN34 · yugos.ai
    Reachable

    Model routing API that picks a model per request across cost, speed and quality, with a CLI for coding agents

    API KeyEndpoint reachable
  9. Green Compute
    SN110 · green-compute.com
    Unreachable

    Per-minute RTX 4090/5090 GPU rentals and hosted open models on miners using verified renewable power

    API KeyDocumented
  10. SOMA
    SN114 · thesoma.ai
    Not checked

    Proxy that compresses context for AI coding agents before requests reach the model, reducing input tokens

    API KeyDocumented