InBoost LongRun Evaluation Runtime

Local context conservation, rate-limit extension, and verification engine for AI coding agents.
(Universal Multi-Platform Binary & Script Distribution Runtime).
Compatible with Claude Code, Google Antigravity (agy), Cursor, Windsurf, and OpenHands.

---

💡 Developer Advantages

Autonomous coding agents burn through token budgets and model rate limits quickly when inspecting unfamiliar codebases and iterating on failing test suites. InBoost LongRun operates as a local intelligence filter and verification layer right on your machine, keeping your agent's context clean, focused, and economical.

• Extended Rate-Limit Runway: Stay productive longer and prevent hitting hourly message caps or quota exhaustion walls during deep refactoring and long-running agent tasks.
• Lower Token Consumption & Costs: Prevent agents from ingesting thousands of redundant tokens from full file dumps and verbose framework test logs.
• Faster Turnaround & Latency: Significantly decrease time-to-first-token and overall turn completion times by maintaining lean context windows.
• Elimination of Wasted Repair Loops: Local syntax and scope verification intercepts broken edits on your CPU before files are saved, eliminating expensive multi-turn roundtrips to fix trivial mistakes.
• 100% Local Privacy Guarantee: All analysis, verification, and filtering routines run entirely on your local CPU. Your code, diffs, and prompts never leave your workstation.

---

📦 Packages & Distribution

InBoost LongRun is distributed across official package registries and standalone binaries:

Registry	Primary Package	Alias / Scoped Packages	Description
npm	inboost-longrun	inboost-ai-longrun @inboost-pro/inboost-longrun @inboost-pro/inboost-ai-longrun	Universal Node.js CLI & npx runner
PyPI	inboost-longrun	inboost-ai-longrun	Python CLI wrapper with native acceleration
Binary Releases	GitHub Releases	Linux (x86_64, ARM64), macOS (Apple Silicon, Intel), Windows	Universal standalone binaries (0 dependencies)

---

🚀 Quick Install

⚡️ 2-Line Zero-Friction Setup (Recommended)

Install globally and run init to automatically configure rules and MCP servers across Claude Code, Cursor, and Antigravity:

npm install -g @inboost-pro/inboost-longrun
inboost-longrun init

Or run instantly with zero installation via npx:

npx @inboost-pro/inboost-longrun init

The init command automatically:

1. Copies optimization directives to global ~/.claude/rules/inboost_longrun.md and ~/.agents/rules/inboost_longrun.md.
2. Configures project directives in .cursorrules and .claude/rules/inboost_longrun.md.
3. Registers the inboost-longrun MCP server inside .cursor/mcp.json.

---

Option 1: Instant Execution via npx

Run directly with zero pre-installation:

# Check evaluation status and remaining runway
npx inboost-longrun status

# Start Model Context Protocol (MCP) server
npx inboost-longrun serve

Or install globally via npm:

npm install -g inboost-longrun
inboost-longrun status

(You can also use the alias package npx inboost-ai-longrun or organization packages npx @inboost-pro/inboost-longrun / npx @inboost-pro/inboost-ai-longrun).

Option 2: Python (pip)

pip install inboost-longrun
inboost-longrun status
inboost-longrun serve

(Alias package pip install inboost-ai-longrun is also available).

Option 3: One-Line Standalone Shell Installers

Linux & macOS:

curl -fsSL https://raw.githubusercontent.com/inboost-dev/inboost-ai-longrun-runtime/main/install.sh | bash

Windows (PowerShell):

irm https://raw.githubusercontent.com/inboost-dev/inboost-ai-longrun-runtime/main/install.ps1 | iex

Option 4: Local Repository Build

git clone https://github.com/inboost-dev/inboost-ai-longrun-runtime.git
cd inboost-ai-longrun-runtime
./install.sh

---

🛠 Model Context Protocol (MCP) Tools

InBoost LongRun integrates seamlessly into your AI assistant or IDE through the standard Model Context Protocol (MCP), providing local tools designed to maximize context economy and coding accuracy:

Tool	Purpose & Developer Advantage
l0_view_outline	Structural Code Inspection: Gives your AI assistant a clear map of symbols, functions, and definitions without spending thousands of tokens reading full file bodies.
l0_clean_test_log	Noise-Free Error Isolation: Strips framework noise from test logs (pytest, unittest, jest) to expose the root-cause failure, preventing context pollution.
l0_verify_syntax	Instant Syntax Guardrail: Verifies code correctness on your local CPU before saving, preventing wasted prompt turns on syntax errors.
l0_verify_edit_scope	Targeted Change Guardrail: Keeps code modifications focused and within budget, stopping runaway diffs before they happen.
l0_run_test	Compact Test Execution: Runs local test suites and returns clean, signal-dense output tailored for agent decision-making.
l0_savings_report	Savings & Quota Ledger: Reports cumulative tokens conserved, quota windows extended, and syntax errors intercepted during your active session.

---

🤖 AI Agent Setup

1. Claude Code

Add the MCP server to Claude Code:

claude mcp add inboost-longrun -- inboost-longrun serve

Add optimization directives to .claude/rules/inboost_longrun.md (or CLAUDE.md):

# InBoost LongRun Optimization Directives

1. Context Conservation: Before reading large files, use l0_view_outline to inspect declarations and structure.
2. Test Failure Isolation: Filter test logs and runtime exceptions via l0_clean_test_log to eliminate noise and isolate failing lines.
3. Syntax Integrity: Validate all code modifications with l0_verify_syntax prior to finalizing changes.
4. Edit Scope Compliance: Ensure edits remain focused and within budget. Verify with l0_verify_edit_scope.
5. Execution Optimization: Run test commands via l0_run_test for compact results. Check session economy with l0_savings_report.

2. Google Antigravity (agy)

Add the MCP server to Antigravity CLI:

agy mcp add inboost-longrun inboost-longrun serve

Rules are automatically loaded from .agents/rules/inboost_longrun.md.

3. Cursor

Add inboost-longrun to your project's .cursor/mcp.json:

{
  "mcpServers": {
    "inboost-longrun": {
      "command": "inboost-longrun",
      "args": ["serve"]
    }
  }
}

---

📦 Supported Platforms

All binaries are standalone, statically compiled or native executables with zero external runtime dependencies:

• Linux: x86_64 & arm64 (Universal Static ELF, zero libc dependencies, runs on Ubuntu, Debian, Alpine, CentOS, Arch, Docker)
• macOS: Apple Silicon (arm64, M1–M4) & Intel (x86_64) (Native Mach-O)
• Windows: x86_64 (Native Console PE32+)

---

🔒 Privacy & Data Security

InBoost LongRun executes 100% locally on your machine and never transmits code externally.

All analysis, verification, and filtering routines run exclusively on your workstation's CPU. The engine makes zero network connections, sends no telemetry, and requires no external API keys.

---

🧪 Testing & Verification

Run the automated test suite to verify binary integrity, Ed25519 license validity, and MCP protocol compliance:

./tests/run_tests.sh

Or via pytest:

pytest tests/ -v

---

⚖️ Evaluation License Terms

Usage of this distribution is subject to the INBOOST LONGRUN EVALUATION LICENSE AGREEMENT:

• Evaluation Purpose Only: Licensed exclusively for evaluation and non-production testing.
• Term Limit: Access is limited to the active evaluation period. Use must cease upon expiration.
• Disclaimer: Provided "AS IS" with no warranties; all liability is disclaimed to the maximum extent permitted by law.
• Public Benchmarks: Publication of benchmark results requires prior written consent from InBoost.
• Contact: For licensing questions or extended enterprise pilots, contact inbound@inboost.pro.