Agent orchestrator · Agent runtime / workspace

inference.sh

inference.sh is an Agent runtime / workspace in the 2026 agents.dancingteeth catalog. Builders who want an agent workspace/runtime with tools, flows, durable session memory, and a belt CLI for compounding skills across runtimes.

Last updated

Best for

Builders who want an agent workspace/runtime with tools, flows, durable session memory, and a belt CLI for compounding skills across runtimes.

Skip if

You only need a cheap OpenAI-compatible inference catalog or a single local coding IDE/CLI.

Who it fits

  • Builders who want an agent workspace/runtime with tools, flows, durable session memory, and a belt CLI for compounding skills across runtimes.
  • Terminal-first engineers who live in the shell and git
  • Builders who start in the browser without a local IDE setup

Pros

AI workspace where agents use real tools (apps/flows/workers); multi-model one API; belt CLI installs evolving skills across Claude Code/Cursor/runtimes; durable agent state that compounds across sessions.

Cons

Workspace BYOK is not an OpenRouter-class inference catalog — and not a drop-in Cursor/Claude Code replacement for git repos alone.

Facts

Locality:
Hybrid (local + cloud)
Surfaces:
CLI, Web
Maturity:
General availability
BYOK:
Bring your own API key
Free tier:
Free option available

Agent standards & memory

AGENTS.md: Delegates to agentsSKILL.md: SupportedRules / memory: Platform skills, knowledge stack, durable agent/session state.Free tier / pay-per-run.

Compare one neighbor first

Vendor pages sell hard. Read one alternative on this site, then leave for the official link if the fit still holds.

Alternatives

Frequently asked questions

What is inference.sh?

inference.sh is an Agent runtime / workspace covered in the agents.dancingteeth 2026 catalog. AI workspace where agents use real tools (apps/flows/workers); multi-model one API; belt CLI installs evolving skills across Claude Code/Cursor/runtimes; durable agent state that compounds across sessions.

Who is inference.sh best for?

Builders who want an agent workspace/runtime with tools, flows, durable session memory, and a belt CLI for compounding skills across runtimes.

When should I skip inference.sh?

You only need a cheap OpenAI-compatible inference catalog or a single local coding IDE/CLI.

What are the main trade-offs of inference.sh?

Pros: AI workspace where agents use real tools (apps/flows/workers); multi-model one API; belt CLI installs evolving skills across Claude Code/Cursor/runtimes; durable agent state that compounds across sessions. Cons: Workspace BYOK is not an OpenRouter-class inference catalog — and not a drop-in Cursor/Claude Code replacement for git repos alone.

Does inference.sh support AGENTS.md, SKILL.md, or MCP?

This card lists AGENTS.md as Delegates to agents, SKILL.md as Supported, and rules/memory as Platform skills, knowledge stack, durable agent/session state.. Free options: Free tier / pay-per-run..

Someone asks you about vibe-coding software? Share this site with them — we are adding more useful data regularly. agents.dancingteeth.net

← Back to full tool directory