# 🖥️ Savant Code — 9 AI Agents That Audit Every Change Before It Touches Your Repo (Free · Local · Open-Source)

**URL:** <https://onehack.st/t/savant-code-9-ai-agents-that-audit-every-change-before-it-touches-your-repo-free-local-open-source/324480>\
**Category:** Tools & Scripts\
**Tags:** programming, ai\
**Created:** [6 أغسطس 2026، 12:38م UTC](https://onehack.st/t/savant-code-9-ai-agents-that-audit-every-change-before-it-touches-your-repo-free-local-open-source/324480 "2026-08-06T12:38:51Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![fame0x](https://onehack.st/user_avatar/onehack.st/fame0x/32/152421_2.png) [@fame0x](https://onehack.st/u/fame0x)\
**Post date:** [6 أغسطس 2026، 12:38م UTC](https://onehack.st/t/savant-code-9-ai-agents-that-audit-every-change-before-it-touches-your-repo-free-local-open-source/324480/1 "2026-08-06T12:38:51Z")

</div>

### 🔴 RED ▸ 🟢 GREEN ▸ 🔍 AUDIT ▸ 🔧 FIX ▸ ✅ DONE

_no code touches your repo until it clears all five — enforced by 9 agents, on your own machine_

Most AI coders are **one model guessing** — they edit, hope, and fail _confidently_. **Savant Code** runs **9 specialized agents** with separated duties that **audit every change before it hits your files**. Local-first (Ollama), Apache-2.0, free.

```bash
npm install -g savant-code
cd your-project && savant-code # auto-detects a running Ollama

```

> 💡 **The insight:** code quality isn’t a _model_ problem, it’s a _harness_ problem — you don’t wait for GPT-6, you engineer a pipeline that catches mistakes structurally. Detective finds bugs _with evidence_ → Forge fixes surgically → a **separate** Verifier audits → self-correct → done. No merge without an independent audit.

> **🔵 The 9 agents + the engineering (for the tinkerers)**
>
> | Agent | Role |
> | --- | --- |
> | 🧭 **Savant** | orchestrator — routes work, enforces protocol |
> | 🔴 **Detective** | RED — finds bugs with evidence · _read-only_ |
> | 🟢 **Forge** | GREEN — implements the converged plan · _write_ |
> | 🔍 **Verifier** | AUDIT — independent double-check afterwards |
> | 🧠🔭🌐🗂✍ **Thinker · Scout · Researcher · Recorder · Scribe** | reason · explore · web-research · track · document |
> 
> - **Tool-permission boundaries** — each agent gets _exactly_ the tools its role allows (allowlist-filtered), no more
> - **Fail-closed streaming** — malformed tool calls are rejected, never coerced
> - **Checkpoint & `/rewind`** — per-turn edit checkpoints (code / convo / both / fork)
> - **Provider-flexible** — Ollama · OpenRouter · NVIDIA NIM · any OpenAI-compatible API
> - **GitHub MCP** (read-only PR/issue/CI review) · **DB helper** (read-only default, LIMIT injection, SQL redaction) · self-contained **HTML reports**
> - TypeScript/ **Bun** · ECHO Protocol v0.2.0 · Apache-2.0

**Grab it →** [GitHub](https://github.com/savant0x/savant-code) · [npm](https://www.npmjs.com/package/savant-code)

_One model guesses. Nine agents cross-examine. Your repo only ever sees what survives the audit._