First LLM Studio

English | 简体中文

English

First LLM Studio is a local-first LLM workbench for Apple Silicon. It brings local MLX runtimes, remote API targets, Agent sessions, Compare, Fine-tune, Benchmark, model discovery, runtime recovery, release evidence, and admin monitoring into one operating surface.

It is not another chat shell. It is built for people who need to compare behavior, debug runtimes, run evals, prepare adapters, and keep local and remote model work inside one product loop.

Product Surfaces

Major Version Story

Current source version: v1.5.1, with source status COMPLETE and local acceptance PASS. The machine-readable release-state.json deliberately separates the active source milestone from the latest public GitHub release (v0.4.0) and the latest desktop candidate (v1.1.0-rc.2).

Internal post-release evidence has advanced through the v1.6.6 benchmark decision-intelligence checkpoint: all 500 stored results are classified (160 correct and 340 mathematical mismatches, with 100% answer extraction), confidence-aware risk highlights Intermediate Algebra, Precalculus, and Level 5, and the conservative 500-sample detectable effect is 8.27 percentage points. Only one distinct complete run exists, so candidate promotion remains EVIDENCE NEEDED. This does not change the active source version or claim hosted leaderboard parity, independent-host reproduction, multimodal execution, distribution, or production promotion.

Latest desktop candidate notes: v1.1.0-rc.2. Distribution remains HOLD and production remains BLOCKED; this repository does not represent missing Apple, organization, non-loopback, distributed-worker, or collaborative receipts as completed evidence.

Competitive Position

Reviewed against official product documentation on 2026-07-12. Core means a first-party primary workflow; integrated means the capability exists but is not the product's deepest specialization; ecosystem means it is normally assembled through adjacent clients or plugins. "Not primary" does not mean technically impossible.

First LLM Studio's advantage is the connected evidence chain across Agent, Compare, Retrieval, Benchmark, Fine-tune, adapter export, Workflow Studio, and release review. Its clearest remaining gaps are signed desktop distribution, heterogeneous runtime production receipts, team identity/governance, collaborative and distributed workflow execution, and real multi-node/cloud evidence. See the full bilingual competitive landscape and product direction, including methodology, limitations, official sources, and the post-v1 adoption principles.

Who It Helps

Local AI builders on Apple Silicon

• Compare MLX local models against hosted APIs under aligned context budgets.
• Inspect runtime cost, prewarm, release, recovery, and hardware pressure without leaving the app.
• Decide which local model is actually usable for daily coding and analysis workflows.

Agent and tooling teams

• Validate tool-calling, repo-grounded behavior, replay, and patch flows in one workbench.
• Turn Compare runs into benchmark handoff without switching products.
• Separate model-quality failures from provider quirks and local runtime instability.

Evaluation and platform engineers

• Run formal and focused benchmark suites with repeatable profiles.
• Review baselines, deltas, run notes, failure classifications, and release evidence.
• Keep local and remote targets inside one comparable target catalog.

Core Value

• Unified local + remote target catalog.
• Compare Lab for model-vs-model output review.
• Fine-tune workflows for datasets, recipes, training, evaluation, adapter proof loops, export, best-checkpoint selection, and LoRA release evidence.
• Visual Workflow Studio for typed Agent/RAG/eval graphs, immutable recipes, guarded tool execution, replay, and OpenAI-compatible deployment.
• Benchmark operations with history, progress, baselines, reports, and release evidence.
• Foreground Retrieval for document import, chunk inspection, and grounded evidence probes.
• Experiments timeline for session/run lineage, artifact navigation, and retention policy.
• Replay, trace review, patch inspection, and exportable review notes.
• Runtime operations for prewarm, release, restart, log inspection, telemetry, and recovery.
• Dynamic local/community model discovery plus remote provider health scanning.

Current Targets

Local

• Local Qwen3 0.6B
• Local Qwen3 4B 4-bit
• Local Qwen3.5 4B 4-bit
• Local Gemma 3 4B It Qat 4-bit

Remote

• OpenAI Codex
• OpenAI GPT-5.5
• Claude API
• DeepSeek API
• Kimi API
• GLM API
• Qwen API

Selection and stability guidance: docs/benchmark-lane-comparison.md.

Contributor onboarding: English · 中文快速上手 · GitHub setup checklist.

Screenshots

Captured from the running local app after npm run typecheck and npm run smoke:routes. README screenshots are generated with npm run screenshots:readme at 2x DPR so text stays sharp on GitHub and ModelScope; the LoRA evidence chart is exported from SVG at 2x DPR.

Agent workbench with target catalog, runtime rail, and tool-enabled composer:

Workflow Graph Studio with draggable typed nodes, version/revision controls, execution recovery, and promotion evidence:

Reproducible motion capture workflow: docs/demo-video-workflow.md.

Watch the Agent workbench MP4 demo · SHA-256 metadata

Fine-tune Studio with workflow tabs, training controls, and report/evidence panels:

Fine-tune completed run with live loss curves, train/validation traces, and handoff actions:

Real Qwen3 4B LoRA release evidence with save/eval markers and selected best checkpoint:

Vector version: fine-tune-qwen4b-lora-chart.svg. Full run archive and manifest: docs/release-evidence/finetune-qwen4b-lora-2026-07-01.

Benchmark Studio with run controls and historical evidence cards:

Benchmark run evidence from a real local smoke run:

Models Studio with immutable Hub/storage receipts, real Ollama Local Server acceptance, and the real MLX/Ollama/llama.cpp Runtime Fabric matrix:

MCP and secure extension acceptance with signed lifecycle, real tool discovery, quarantine defenses, and explicit production gates:

Compare, Retrieval, and Admin surfaces:

Quick Start

Requirements

• macOS on Apple Silicon
• Node 22.x
• Python 3.12
• MLX-compatible local environment

Install

nvm install 22
nvm use 22
npm install
cp .env.example .env.local

Start the web app

npm run dev

Default routes:

• http://localhost:3011/agent
• http://localhost:3011/compare
• http://localhost:3011/fine-tune
• http://localhost:3011/models
• http://localhost:3011/benchmarks
• http://localhost:3011/retrieval
• http://localhost:3011/experiments
• http://localhost:3011/admin

Start the local model gateway

python3 -m venv .venv
source .venv/bin/activate
pip install -U pip
pip install mlx mlx-lm
python scripts/local_model_gateway_supervisor.py

If your preferred Python is outside PATH, set LOCAL_AGENT_PYTHON_BIN before starting the app or gateway.

Gateway health:

• http://127.0.0.1:4000/health

Verification

npm run typecheck:changed
npm run smoke:routes
npm run smoke:screenshots

Configuration

Copy .env.example to .env.local and fill only the providers you want to use.

Important notes:

• .env.local is ignored by git.
• Remote providers are optional.
• Several targets use OpenAI-compatible or Claude-compatible endpoints.
• Public defaults in this repository are sanitized placeholders.

Repository Structure

app/                      Next.js app routes and thin API transports
components/               Shared UI and compatibility shells
features/                 Feature-owned routes, contracts, state, actions, and application ports
lib/agent/                Agent runtime, providers, benchmark, gateway helpers
lib/finetune/             Fine-tune store facade and split operation services
scripts/                  Local gateway, runtime, verification, and release scripts
docs/                     Architecture, release notes, launch notes, roadmap, and assets
modelscope/               ModelScope profile/readme metadata
public/                   Public assets and social cover art

Distribution

• GitHub: https://github.com/ChrisChen667788/Your-First-LLM-Studio
• ModelScope profile: https://www.modelscope.cn/profile/haozi667788
• Default ModelScope repo id: haozi667788/first-llm-studio

The ModelScope package script exports the committed Git tree so GitHub and ModelScope can stay file-identical for each synced version.

Security and Privacy

• Sensitive local actions require confirmation.
• Secrets belong in .env.local.
• Public repository defaults are sanitized.
• New public commits should use a GitHub noreply address where possible.
• See SECURITY.md.

Contributing

Issues and PRs are welcome.

• CONTRIBUTING.md
• CODE_OF_CONDUCT.md
• docs/open-source-backlog.md

Release Notes

• Current version: VERSION
• Release notes: docs/releases
• Release process: docs/release-process.md
• Active source: v1.5.1; latest public GitHub release: v0.4.0; latest desktop candidate: v1.1.0-rc.2

简体中文

First LLM Studio 是一个面向 Apple Silicon 的本地优先 LLM 工作台。它把本地 MLX 运行时、远端 API 目标、Agent 会话、Compare 对比、Fine-tune 微调、Benchmark 评测、模型发现、runtime 恢复、发布证据和后台监控统一到一个产品界面里。

它不是另一个聊天壳，而是给真正需要比较模型行为、调试 runtime、跑评测、准备 adapter，并把本地/远端模型工作流收在同一个产品循环里的开发者使用。

产品入口

大版本核心功能

当前源码版本：v1.5.1，源码状态为 COMPLETE、本地验收为 PASS。机器可读的 release-state.json 明确区分当前源码里程碑、最近公开 GitHub Release（v0.4.0）与最近桌面候选包（v1.1.0-rc.2）。

内部后续证据已推进到 v1.6.6 Benchmark 决策智能检查点：500 条结果全部完成分类（160 正确、340 条数学不等价，答案提取覆盖 100%），置信区间规则标出 Intermediate Algebra、Precalculus 与 Level 5 风险，500 样本下的保守可检测变化约为 8.27 个百分点。当前只有一个不同 run id 的完整运行，因此候选晋级继续为 EVIDENCE NEEDED。该检查点不改变当前源码版本，也不宣称托管榜单等价、独立主机复现、多模态全量执行、分发或生产晋级。

最新桌面候选说明：v1.1.0-rc.2。分发状态继续为 HOLD、生产状态继续为 BLOCKED；仓库不会把缺失的 Apple、组织、非回环、分布式 worker 或多人协作 receipt 表述为已完成证据。

竞品定位对比

本表基于 2026-07-12 可查的官方产品文档。核心表示产品原生主流程，已集成表示具备能力但不是最深的专长，生态表示通常依赖相邻客户端或插件组装。“非主线”不等于技术上完全不能实现。

First LLM Studio 的优势是把 Agent、Compare、Retrieval、Benchmark、Fine-tune、adapter export、Workflow Studio 和 release review 接成一条证据链。当前最明确的剩余短板是签名桌面分发、异构 runtime 生产证据、团队身份与治理、协同/分布式 workflow 执行，以及真实多节点/云生产证据。完整方法、优劣势、官方来源和 post-v1 借鉴原则见双语文档：竞品格局与产品方向。

对哪些用户有价值

Apple Silicon 本地 AI 开发者

• 在统一上下文预算下，对比 MLX 本地模型和托管 API。
• 不离开应用就能查看 runtime 成本、prewarm、release、恢复动作和硬件压力。
• 判断哪个本地模型真的适合日常 coding / analysis 工作流。

Agent / 工具链团队

• 在一个工作台里验证 tool calling、repo-grounded behavior、replay 和 patch 流程。
• 直接把 Compare 结果送入 Benchmark，不必切换产品。
• 区分失败来源：模型质量、provider 行为，还是本地 runtime 不稳。

评测 / 平台工程团队

• 用可复现 profile 跑 formal 和 focused benchmark suites。
• 查看 baseline、delta、run note、失败分类和发布证据。
• 让本地与远端 target 落在同一个可比较的 target catalog 里。

核心价值

• 本地 + 远端统一 target catalog。
• Compare Lab 支持模型对模型审阅。
• Fine-tune 工作流覆盖 dataset、recipe、training、evaluation、adapter proof loop、export、best-checkpoint 选择和 LoRA 发布证据。
• 可视化 Workflow Studio 覆盖 Agent/RAG/eval 类型图、不可变 recipe、受保护工具执行、回放与 OpenAI-compatible 部署。
• Benchmark 运维覆盖 history、progress、baseline、report 和 release evidence。
• Retrieval 前台覆盖文档导入、chunk 检查和 grounded evidence probe。
• Experiments 时间线覆盖 Session/Run lineage、artifact 导航和 retention policy。
• Replay、trace review、patch inspection 与可导出的审阅记录。
• Runtime 运维覆盖 prewarm、release、restart、日志检查、telemetry 和 recovery。
• 支持本地/社区模型发现和远端 provider health 扫描。

当前支持的 Target

本地

• Local Qwen3 0.6B
• Local Qwen3 4B 4-bit
• Local Qwen3.5 4B 4-bit
• Local Gemma 3 4B It Qat 4-bit

远端

• OpenAI Codex
• OpenAI GPT-5.5
• Claude API
• DeepSeek API
• Kimi API
• GLM API
• Qwen API

Target 选择、稳定性与适用任务对照：docs/benchmark-lane-comparison.md。

贡献者入口：English · 中文快速上手 · GitHub 仓库设置清单。

截图

以下截图来自本地运行版本，并已通过 npm run typecheck 与 npm run smoke:routes。README 截图使用 npm run screenshots:readme 以 2x DPR 生成，LoRA 证据图从 SVG 以 2x DPR 导出，确保在 GitHub 和 ModelScope 缩放后文字仍然清晰。

Agent 工作台：target catalog、runtime rail 与工具化输入区：

Workflow Graph Studio：可拖拽类型节点、版本/修订控制、执行恢复与 promotion evidence：

可复现动态演示流程：docs/demo-video-workflow.md。

查看 Agent 工作台 MP4 演示 · SHA-256 元数据

Fine-tune Studio：工作流 tab、训练控制与 report/evidence 面板：

Fine-tune 完成作业：真实 loss 曲线、训练/验证轨迹与 handoff 操作：

真实 Qwen3 4B LoRA 发布证据：包含 save/eval 事件标记和自动选择的最佳 checkpoint：

矢量版本：fine-tune-qwen4b-lora-chart.svg。完整 run archive 与 manifest：docs/release-evidence/finetune-qwen4b-lora-2026-07-01。

Benchmark Studio：运行控制与历史证据卡片：

Benchmark：本地 smoke run 生成的真实评测证据：

Models Studio：不可变 Hub/外置盘证据、真实 Ollama Local Server 验收，以及真实 MLX/Ollama/llama.cpp Runtime Fabric 矩阵：

MCP 与安全扩展验收：签名生命周期、真实工具发现、隔离/检疫防御和显式生产门禁：

Compare、Retrieval 与 Admin：

快速开始

环境要求

• Apple Silicon macOS
• Node 22.x
• Python 3.12
• 可运行 MLX 的本地环境

安装

nvm install 22
nvm use 22
npm install
cp .env.example .env.local

启动 Web 应用

npm run dev

默认入口：

• http://localhost:3011/agent
• http://localhost:3011/compare
• http://localhost:3011/fine-tune
• http://localhost:3011/models
• http://localhost:3011/benchmarks
• http://localhost:3011/retrieval
• http://localhost:3011/experiments
• http://localhost:3011/admin

启动本地模型网关

python3 -m venv .venv
source .venv/bin/activate
pip install -U pip
pip install mlx mlx-lm
python scripts/local_model_gateway_supervisor.py

如果 Python 不在 PATH 中，可以在启动前设置 LOCAL_AGENT_PYTHON_BIN 指向实际解释器。

网关健康检查：

• http://127.0.0.1:4000/health

验证

npm run typecheck:changed
npm run smoke:routes
npm run smoke:screenshots

配置说明

把 .env.example 复制成 .env.local，只填写你要启用的 provider 即可。

需要注意：

• .env.local 已被 git 忽略。
• 远端 provider 是可选的。
• 部分 target 走 OpenAI-compatible / Claude-compatible endpoint。
• 本仓库公开版本已经做过脱敏，占位值需要替换成你自己的 endpoint。

仓库结构

app/                      Next.js app routes 与 thin API transports
components/               共享 UI 与兼容 shell
features/                 feature-owned routes、contracts、state、actions、application ports
lib/agent/                Agent runtime、providers、benchmark、gateway helpers
lib/finetune/             Fine-tune store facade 与拆分后的 operation services
scripts/                  本地网关、runtime、验证和发布脚本
docs/                     架构、release notes、launch notes、roadmap 和 assets
modelscope/               ModelScope 主页/readme 元数据
public/                   对外资源和社媒封面图

发布与同步

• GitHub: https://github.com/ChrisChen667788/Your-First-LLM-Studio
• ModelScope profile: https://www.modelscope.cn/profile/haozi667788
• 默认 ModelScope repo id: haozi667788/first-llm-studio

ModelScope 打包脚本会导出已提交的 Git tree，因此每次同步都可以让 GitHub 和 ModelScope 保持同一份文件快照。

安全和隐私

• 敏感本地操作默认需要确认。
• Secret 应保存在 .env.local。
• 公开仓库默认配置已经做过脱敏。
• 新增公开提交应尽量使用 GitHub noreply 地址。
• 见 SECURITY.md。

贡献

欢迎 issue 和 PR。

• CONTRIBUTING.md
• CODE_OF_CONDUCT.md
• docs/open-source-backlog.md

发布说明

• 当前版本：VERSION
• Release notes：docs/releases
• 发布流程：docs/release-process.md
• 当前源码：v1.5.1；最近公开 GitHub Release：v0.4.0；最近桌面候选包：v1.1.0-rc.2