tokenhop
Entry point for tokenhop — local/remote AI gateway with OpenAI-compatible REST for chat, image, TTS, embeddings, web search, web fetch.
Skill by tokenhop
Chalk Labs
Need help deploying tokenhop?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/tokenhop-tokenhop
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: backend, writing
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/tokenhop
What's inside
- Skill name
tokenhop- Description
- Entry point for tokenhop — local/remote AI gateway with OpenAI-compatible REST for chat, image, TTS, embeddings, web search, web fetch. Use when the user mentions tokenhop, TOKENHOP_URL, or wants AI without writing provider boilerplate. This skill covers setup + indexes capability skills; fetch the relevant capability SKILL.md from the URLs below when needed.
- License
- MIT
- Instructions
- 77 lines in SKILL.md · view on GitHub
Before installing
- Instructions call the network
Files (1)
- SKILL.md
SKILL.md (first lines)
# tokenhop
Local/remote AI gateway exposing OpenAI-compatible REST. One key, many providers, auto-fallback.
## Setup
```bash
export TOKENHOP_URL="http://localhost:20128" # or VPS / tunnel URL
export TOKENHOP_KEY="sk-..." # from Dashboard → Keys (only if requireApiKey=true)
```
Older setups may only have the legacy names. When `TOKENHOP_URL` / `TOKENHOP_KEY` are unset, fall back to them:
```bash
export TOKENHOP_URL="${TOKENHOP_URL:-$NINEROUTER_URL}" # legacy(9router): remove in v2
export TOKENHOP_KEY="${TOKENHOP_KEY:-$NINEROUTER_KEY}" # legacy(9router): remove in v2
```
All requests: `${TOKENHOP_URL}/v1/...` with header `Authorization: Bearer ${TOKENHOP_KEY}` (omit if auth disabled).
Verify: `curl $TOKENHOP_URL/api/health` → `{"ok":true}`
## Discover models
```bash
curl $TOKENHOP_URL/v1/models # chat/LLM (default)
curl $TOKENHOP_URL/v1/models/image # image-gen
curl $TOKENHOP_URL/v1/models/tts # text-to-speech
curl $TOKENHOP_URL/v1/models/embedding # embeddings
curl $TOKENHOP_URL/v1/models/web # web search + fetch (entries have `kind` field)
curl $TOKENHOP_URL/v1/models/stt # speech-to-text
curl $TOKENHOP_URL/v1/models/image-to-text # vision
```
Use `data[].id` as `model` field in requests. Combos appear with `owned_by:"combo"`.
Response shape:
```json
{
"object": "list",
"data": [
{ "id": "openai/gpt-5", "object": "model", "owned_by": "openai", "created": 1735000000 },
{
"id": "tavily/search",
"object": "model",
"kind": "webSearch",
"owned_by": "tavily",
"created": 1735000000
}
]
}
```
## Capability skills
When the user needs a specific capability, fetch that skill's `SKILL.md` from the
same gateway base you were given this file from (`<same-base>/skills/<id>/SKILL.md`):
| Capability | Path |
| -------------------------- | -------------------------------------- |
| Chat / code-gen | `/skills/tokenhop-chat/SKILL.md` |
| Image generation | `/skills/tokenhop-image/SKILL.md` |
| Video generation | `/skills/tokenhop-video/SKILL.md` |
| Text-to-speech | `/skills/tokenhop-tts/SKILL.md` |
| Speech-to-text | `/skills/tokenhop-stt/SKILL.md` |
| Embeddings | `/skills/tokenhop-embeddings/SKILL.md` |
| Web search | `/skills/tokenhop-web-search/SKILL.md` |
| Web fetch (URL → markdown) | `/skills/tokenhop-web-fetch/SKILL.md` |
## Errors
- 401 → set/refresh `TOKENHOP_KEY` (Dashboard → Keys)
- 400 `Invalid model format` → check `model` exists in `/v1/models/<kind>`
- 503 `All accounts unavailable` → wait `retry-after` or add another provider accountFrom tokenhop/tokenhop, MIT.
More from tokenhop/tokenhop
- 0.587score
tokenhop-stt
tokenhop
Speech-to-text via tokenhop /v1/audio/transcriptions using OpenAI Whisper / Groq / Gemini / Deepgram / AssemblyAI / NVIDIA / HuggingFace models.
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
tokenhop-chat
tokenhop
Chat / code generation via tokenhop using OpenAI /v1/chat/completions or Anthropic /v1/messages format with streaming + auto-fallback combos.
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
tokenhop-embeddings
tokenhop
Generate vector embeddings via tokenhop /v1/embeddings using OpenAI / Gemini / Mistral / Voyage / Nvidia / GitHub embedding models for RAG, semantic search…
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
tokenhop-video
tokenhop
Generate videos via tokenhop /v1/videos/generations using xAI Grok Imagine (grok-imagine-video).
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
tokenhop-web-fetch
tokenhop
Fetch URL → markdown / text / HTML via tokenhop /v1/web/fetch using Ollama Cloud / Firecrawl / Jina Reader / Tavily Extract / Exa Contents.
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
tokenhop-web-search
tokenhop
Web and X search via tokenhop /v1/search using Tavily / Exa / Brave / Serper / SearXNG / Google PSE / Linkup / SearchAPI / You.com / Perplexity / Xquik.
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
tokenhop-tts
tokenhop
Text-to-speech via tokenhop /v1/audio/speech using OpenAI / ElevenLabs / Deepgram / Edge TTS / Google TTS / Hyperbolic / Inworld voices.
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
tokenhop-image
tokenhop
Generate images via tokenhop /v1/images/generations using OpenAI / Gemini Imagen / DALL-E / FLUX / MiniMax / SDWebUI / ComfyUI / Codex models.
SkillAFreshness: A★ 1Claude Code +9 - 0.579score
9router-video
tokenhop
This skill moved to tokenhop-video.
SkillAFreshness: A★ 1Claude Code +9 - 0.579score
9router-web-fetch
tokenhop
This skill moved to tokenhop-web-fetch.
SkillAFreshness: A★ 1Claude Code +9 - 0.579score
9router
tokenhop
This skill moved to tokenhop.
SkillAFreshness: A★ 1Claude Code +9 - 0.579score
9router-chat
tokenhop
This skill moved to tokenhop-chat.
SkillAFreshness: A★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 1
- Open issues
- 7
- Last commit (this folder)
- Oct 2, 2026 (29 days ago)
- Last release
- Oct 23, 2026 (8 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/tokenhop/tokenhop
- Website
- tokenhop.dev
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from tokenhop
- 0.587score
tokenhop-chat
tokenhop
Chat / code generation via tokenhop using OpenAI /v1/chat/completions or Anthropic /v1/messages format with streaming + auto-fallback combos.
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
tokenhop-embeddings
tokenhop
Generate vector embeddings via tokenhop /v1/embeddings using OpenAI / Gemini / Mistral / Voyage / Nvidia / GitHub embedding models for RAG, semantic search…
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
tokenhop-stt
tokenhop
Speech-to-text via tokenhop /v1/audio/transcriptions using OpenAI Whisper / Groq / Gemini / Deepgram / AssemblyAI / NVIDIA / HuggingFace models.
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
tokenhop-image
tokenhop
Generate images via tokenhop /v1/images/generations using OpenAI / Gemini Imagen / DALL-E / FLUX / MiniMax / SDWebUI / ComfyUI / Codex models.
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
tokenhop-tts
tokenhop
Text-to-speech via tokenhop /v1/audio/speech using OpenAI / ElevenLabs / Deepgram / Edge TTS / Google TTS / Hyperbolic / Inworld voices.
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
tokenhop-video
tokenhop
Generate videos via tokenhop /v1/videos/generations using xAI Grok Imagine (grok-imagine-video).
SkillAFreshness: A★ 1Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get tokenhop running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
tokenhop skill. Agent Mart. https://agentmart.dev/skills/tokenhop-tokenhop (last updated 2026-10-24)