Run agents, intelligently. Make them better.

Tangle runs your agents in isolated sandboxes and turns every trace into proven improvements.

We optimize agents while they run.

Coding harnesses, tool-calling agents, long-running workflows: each gets a real computer in a Tangle Sandbox, and every run generates traces.

Claude Code $ claude running

Codex $ codex running

OpenCode $ opencode running

Hermes $ hermes running

OpenClaw $ openclaw running

NanoClaw $ nanoclaw running

Kimi Code $ kimi running

Pi $ pi running

Every run makes your agents better.

Your agents generate traces

Every sandbox run and every routed model call produces a full session trace: each span, tool call, token, and cost.

checkout-agent · claude38.2s

run · fix flaky checkout test 38.2s

claude-sonnet-5 · plan 2.1s

read · checkout.test.ts 0.5s

pnpm test · full suite 12.8s

edit · retry-policy.ts 1.9s

pnpm test · full suite 11.4s

edit · checkout.test.ts 0.9s

pnpm test · full suite 8.9s

Analysts find what repeats

Analyst agents and RLMs read every trace and cluster the waste and failures that keep coming back.

checkout-agent · claude38.2s

run · fix flaky checkout test 38.2s

claude-sonnet-5 · plan 2.1s

read · checkout.test.ts 0.5s

pnpm test · full suite 12.8s

edit · retry-policy.ts 1.9s

pnpm test · full suite 11.4s

edit · checkout.test.ts 0.9s

pnpm test · full suite 8.9s

Improvements ship where you work

A pull request on GitHub, an issue in Linear, a sharper skill, a summary in Slack. You approve each change, or it ships on its own.

Pull requestmerged

tangle/faster-test-loop

Run the failing test file after each edit. Full suite once before finishing.

Issuedone

TAN-312

Adopt the failing-test-first loop across all coding agents.

Skill updatedlive

skills/testing.md

New testing skill ships to every sandbox image.

#eng-agentsposted

summary

Shipped failing-test-first loop. Held-out evals pass, no completion drop.

Tangle builds infrastructure for self-improving AI systems.

Sandboxes

Isolated computers for agents: shell, files, browser, any coding harness.

sandbox.tangle.tools

Intelligence

Analyst agents mine your traces, propose changes, and prove them on held-out runs.

intelligence.tangle.tools

Inference

477+ models behind one OpenAI-compatible key.

router.tangle.tools

Simple, usage-based pricing.

Start free. Every plan includes monthly credit and pays the same per-second compute rates.

Free

$0/mo

Get started with Tangle.

$2 in monthly credit
1 concurrent sandbox
60 requests / minute
Community support

Start free

Run agents, intelligently.

Get started Read the docs