CacheForge is a token optimization gateway that streamlines onboarding and operations for OpenAI-compatible agent workflows.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install cacheforge
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install cacheforge using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is CacheForge?
CacheForge serves as the foundational entrypoint for managing LLM efficiency within your development environment. It functions as an OpenAI-compatible gateway designed specifically for agent workflows, helping developers reduce wasted spend and improve performance through intelligent caching and routing. By minimizing unnecessary token consumption, it allows for more cost-effective scaling of complex AI applications.
As a central hub among Openclaw Skills, it coordinates specialized sub-skills to handle setup, billing, and telemetry dashboarding. This modular approach ensures that users can easily bootstrap their environment and immediately begin tracking savings and optimizing their upstream provider configurations, such as Anthropic or OpenRouter.
CacheForge Use Cases
- Reducing operational costs for high-volume LLM agent workflows through token optimization.
- Improving performance and response times for repeat-turn agent interactions.
- Managing multiple upstream providers and API keys through a single, unified gateway.
- Monitoring real-time savings and token usage via a centralized telemetry dashboard.
- Implementing Vault Mode for tool-heavy agents requiring specialized optimization.
How CacheForge Works
- The user initiates the skill, which automatically checks for and bootstraps essential companion Openclaw Skills including setup, ops, and stats modules.
- The system routes user requests to the appropriate sub-module based on whether the task involves onboarding, account operations, or usage analysis.
- It acts as an intermediary proxy for all LLM requests, applying optimization logic to reduce costs before forwarding requests to upstream providers.
- Detailed telemetry is captured for every interaction, allowing the stats module to generate comprehensive savings reports.
CacheForge Setup
To begin using this skill, first install the primary package via your CLI:
clawhub install cacheforge
Once installed, you must bootstrap the companion Openclaw Skills to enable full functionality:
bash "{baseDir}/scripts/bootstrap-companions.sh"
If manual installation is preferred or if automated bootstrapping is unavailable, run the following command:
for s in cacheforge-setup cacheforge-ops cacheforge-stats; do clawhub install "$s"; done
CacheForge Data Schema & Taxonomy
CacheForge maintains a structured data hierarchy across its companion modules to ensure efficient operations:
| Component | Responsibility | Primary Interface |
|---|---|---|
| cacheforge-setup | Handles tenant provisioning and provider configuration | setup.py |
| cacheforge-ops | Manages API keys, billing top-ups, and upstream routing | ops.py |
| cacheforge-stats | Tracks usage telemetry and calculates cost savings | dashboard.py |
The system enforces a specific onboarding flow: Registration -> API Key Generation -> Upstream Configuration -> Provider Application -> Credit Top-up -> Validation.
CacheForge Advanced Features
- Vault Mode (Pro) for enhanced optimization of tool-intensive agent workflows.
- Multi-provider routing support for OpenRouter, Anthropic, and custom OpenAI-compatible endpoints.
- Granular usage breakdowns filterable by model, time window, and specific agent tasks.
- Automated OpenClaw provider configuration with built-in backup and validation guards.
- Support for multiple payment methods including Stripe and cryptocurrency for credit top-ups.
SKILL.md
Loading
Related Openclaw Skills
vibe-check
An automated auditing tool that identifies unreviewed AI-generated code patterns and produces a scored quality report card.
CacheForge Stats
A terminal-based dashboard for monitoring CacheForge LLM usage, token savings, and performance metrics.
CacheForge Setup
A streamlined onboarding tool to register, configure, and integrate CacheForge as an LLM proxy for AI agents.
CacheForge Ops
A comprehensive operational toolkit for managing CacheForge account billing, credits, and upstream provider configurations.
Context Engineer
A powerful context window optimizer designed to analyze, audit, and compress AI agent token utilization.
continuity-kernel
A high-reliability continuity kernel providing fail-open context injection, deterministic state persistence, and shadow-mode evaluation receipts.
METADATA
Featured*
