I Built KIRA: A Local-First AI Agent That Has to Prove Its Work
说明与用途
KIRA 是一个本地优先的 AI 代理,通过真实工具输出验证任务完成,提供透明且权限受控的交互。
问题
AI assistants often claim to have completed tasks without verifiable evidence, making it hard to trust their actions.
结果
KIRA demonstrates a reproducible, permission‑aware local AI agent that can be tested on real workflows, providing transparent evidence of task completion.
工作流
- 1. User states a goal
- 2. Orchestrator V1 selects next tool
- 3. KIRA runs the tool with permission gates
- 4. Tool returns real result
- 5. Orchestrator evaluates evidence
- 6. Repeat until task genuinely complete
证据
KIRA should not say a task is complete unless the runtime has evidence from the tool that performed it.
The installer downloads Orchestrator V1 into a local model directory.
KIRA keeps mutating file, command, IDE, MCP, and automation actions behind explicit permission gates.
- 记录日期: 2026-09-18T18:00:37.705Z