# agentbelt 0.3.0: token optimization for local AI agents, with honest numbers

> Source: <https://dev.to/plova_rama_5254efcc1133ae/agentbelt-030-token-optimization-for-local-ai-agents-with-honest-numbers-3kfa>
> Published: 2026-11-14 08:08:07+00:00

[agentbelt](https://github.com/LovaRK/agentbelt) gives every AI coding app (Claude Code, Codex, Cursor, Copilot, DeepSeek, LM Studio) the same safe, audited dev tools over MCP. Version 0.2.0 added **context compaction** for agents running on local models with small context windows (gpt-oss 20B, 16k context, on a MacBook Air). 0.3.0 adds a Goose adapter and a demo GIF.

I ran the same tasks with compaction off and on, 3 runs each. Token counts are what Ollama itself reported.

| Task | Compaction | Correct | Avg input tokens | Largest prompt | 
|---|---|---|---|---|
| read 5 files | off | 3/3 | 46,916 | 13,317 | 
| read 5 files | on | 3/3 | 50,410 | 10,269 | 
| failing test log, twice | off | 1/3 | 42,267 | 6,182 | 
| failing test log, twice | on | 1/3 | 18,448 | 3,338 | 

**Takeaway:** for local agents, the biggest win is not repeating the same logs. Shrinking file contents can backfire.

Full method and raw results: [docs/token-optimization.md](https://github.com/LovaRK/agentbelt/blob/main/docs/token-optimization.md)

```
npx agentbelt setup
```

Then ask your AI app: "Use agentbelt's agent_run with compact: true to …"

⭐ If this is useful, a star on [GitHub](https://github.com/LovaRK/agentbelt) helps other developers find it. And if you run agents on local models, I'd love to hear what you've measured.