# T3 Code (slim)

> T3 Code is an open-source control surface for the coding agents on your machine, Claude Code, Codex, Cursor, Grok Build, OpenCode, Antigravity and fx, from desktop, web and iOS and Android apps.

- Full: https://www.anchorterminal.com/tools/t3-code.md (~4,800 tokens) · this version ~930 tokens · JSON https://www.anchorterminal.com/tools/t3-code.json · canonical https://www.anchorterminal.com/tools/t3-code
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · MCP: https://www.anchorterminal.com/mcp · Updated: 2026-11-07 · pricing https://www.anchorterminal.com/tools/t3-code#pricing · reviews https://www.anchorterminal.com/tools/t3-code#reviews
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)

**D · 51.9/100 · rank #1002 of 1486 · #40 in Agent harnesses · not agent-ready · confidence low**


Assessment: A fast-moving open-source way to run and steer several coding agents from desktop, browser or phone, using the subscriptions you already have. It's pre-1.0, and it sends usage data by default, including hashed identifiers for your OpenAI and Claude accounts, with the opt-out documented outside the README.

## Facts

- Kind: Agent harness · vendor: T3 Tools Inc. · category: Agent harnesses · legal entity: T3 Tools Inc. · provenance 40/100
- Auth: None · pricing: Free · x402: no · licence: MIT
- Benchmark probes: not run yet, so Performance is pending
- Surface graded: The open-source app, read from a shallow clone of github.com/pingdotgg/t3code on 7 November 2026. Nothing installed
- Providers: Codex, Claude Code, Cursor, Grok Build, OpenCode, Google Antigravity and fx, each installed and logged in on the machine running the server

- Scores: Reliability 43, Performance pending, Schema & documentation 55, Agent ergonomics 60, Security & auth 35, Payments & pricing 60, Task success pending, Maintenance & community 75, Transparency & trust 51 · total over the 7 assessed categories
- Why: Reliability, Local software. · Schema & documentation, Harness reading. · Agent ergonomics, Harness reading. · Security & auth, Harness reading. · Payments & pricing, Free self-hosted software with nothing to buy, so 0 for a protocol and 20 each for public pricing, a free tier and onboarding with no sign-u… · Maintenance & community, Commits and nightly tags on 6 November 2026 (30). · Transparency & trust, MIT (30).
- Sources: 2, open questions: 1, both in the full twin
- Capabilities: agent.harness, agent.multi-agent
- JSON: https://www.anchorterminal.com/api/v1/tools/t3-code.json
- Verify (for the vendor): the badge `https://www.anchorterminal.com/badges/t3-code.svg` or a link to https://www.anchorterminal.com/tools/t3-code from a page on t3.codes or one of its subdomains, or the README at the root of github.com/pingdotgg/t3code, then `POST https://www.anchorterminal.com/api/v1/verify` `{"slug", "url"}` or `verify_listing` at /mcp; re-checked weekly, no effect on the grade. Snippets in the full twin.

## Before you call it

1. Set T3CODE_TELEMETRY_ENABLED=false before starting the server if you don't want usage events sent
2. Install and log in to at least one provider CLI first, such as codex login or claude auth login
3. Use a managed policy to fix settings across a team

## Connect

```bash
curl -fsSL https://t3.codes/install.sh | sh
```

## Similar tools

| Tool | Grade | Score | Shared capabilities | Slim |
| --- | --- | --- | --- | --- |
| goose | BB | 71.3 | agent.harness, agent.multi-agent | https://www.anchorterminal.com/tools/goose.min.md |
| AXLR | BB | 70.6 | agent.harness, agent.multi-agent | https://www.anchorterminal.com/tools/axlr.min.md |
| OpenHands | BB | 70.3 | agent.harness, agent.multi-agent | https://www.anchorterminal.com/tools/openhands.min.md |
| OpenCode | B | 68.8 | agent.harness, agent.multi-agent | https://www.anchorterminal.com/tools/opencode.min.md |
| Qwen Code | B | 68.7 | agent.harness, agent.multi-agent | https://www.anchorterminal.com/tools/qwen-code.min.md |


## Panel reviews (0, desk reviews from public material, no calls made)