Skillget

forge

mcp
Guvenlik Denetimi
Gecti
Health Gecti
  • License — License: Apache-2.0
  • Description — Repository has a description
  • Active repo — Last push 0 days ago
  • Community trust — 12 GitHub stars
Code Gecti
  • Code scan — Scanned 12 files during light audit, no dangerous patterns found
Permissions Gecti
  • Permissions — No dangerous permissions requested
Purpose

This tool is a secure, portable runtime for building and deploying AI agents from a single configuration file. It is designed to run these agents locally, in the cloud, or in air-gapped enterprise environments without exposing inbound network tunnels.

Security Assessment

Overall Risk: Medium. The tool is designed with strong security principles, such as outbound-only connections, encrypted secrets, and artifact signing. However, because it orchestrates and runs AI agents, it inherently processes data and executes actions (like subprocess proxying and cron scheduling) based on user inputs. The automated code scan found no dangerous patterns, hardcoded secrets, or dangerous permission requests. Network requests are heavily featured but appear strictly controlled via egress allowlists. As with any AI agent runtime, there is inherent risk in the prompts and skills it executes, so users must trust the agent definitions they provide.

Quality Assessment

The project demonstrates good overall health. It is actively maintained, with repository activity as recent as today. It uses the permissive Apache-2.0 license, making it highly suitable for both open-source and enterprise adoption. The project has a small but growing community, currently backed by 12 GitHub stars, which indicates early-stage validation rather than widespread community trust.

Verdict

Safe to use, provided you review the specific AI skills and configurations you instruct it to run.
SUMMARY

Forge - OpenClaw for Enterprise: Forge is a secure, portable AI Agent runtime. Run agents locally, in cloud, or enterprise environments without exposing inbound tunnels.

README.md

Forge — OpenClaw for Enterprise: A Secure, Portable AI Agent Runtime

Build, run, and deploy AI agents from a single SKILL.md file.
Secure by default. Runs anywhere — local, container, cloud, air-gapped.

Why Forge?

  • 60-second setup — forge init wizard configures provider, keys, channels, and skills
  • Secure by default — outbound-only connections, egress allowlists, encrypted secrets, no public listeners
  • Portable — same agent runs locally, in Docker, Kubernetes, or inside Initializ Command
  • Observable — structured NDJSON audit logs with correlation IDs for every action
  • Extensible — add skills, tools, channels, and LLM providers without changing core code

Quick Start

# Install (pick one)
brew install initializ/tap/forge
curl -sSL https://raw.githubusercontent.com/initializ/forge/main/install.sh | bash

# Create and run an agent
forge init my-agent && cd my-agent && forge run

# Connect to Slack
forge run --with slack

See Quick Start for the full walkthrough, or Installation for all methods.

How It Works

SKILL.md --> Parse --> Discover tools/requirements --> Compile AgentSpec
                                                            |
                                                            v
                                                    Apply security policy
                                                            |
                                                            v
                                                    Run LLM agent loop
                                               (tool calling + memory + cron)

You write a SKILL.md. Forge compiles it into a secure, runnable agent with egress controls, encrypted secrets, and audit logging.

Key Features

Feature Description
Atomic Skills SKILL.md-based agent definitions with YAML frontmatter
Egress Security Runtime + build-time domain allowlists with subprocess proxy
Channel Connectors Slack (Socket Mode), Telegram (polling) — outbound-only
Cron Scheduling Recurring tasks with channel delivery
Memory Session persistence + long-term vector search
LLM Fallbacks Multi-provider with automatic failover
Web Dashboard forge ui for browser-based agent management
Build Signing Ed25519 artifact signing & verification
Air-Gap Ready Runs with local models, no cloud required

Documentation

Getting Started

Document Description
Quick Start Get an agent running in 60 seconds
Installation Homebrew, binary, and Windows install
Architecture System design, module layout, and data flows

Core Concepts

Document Description
Skills Skill definitions, registry, and compilation
Tools Built-in tools, adapters, and custom tools
Runtime LLM providers, fallback chains, running modes
Memory Session persistence and long-term memory
Channels Slack and Telegram adapter setup
Scheduling Cron configuration and schedule tools

Security

Document Description
Security Overview Complete security architecture
Egress Security Egress enforcement deep dive
Secrets Encrypted secret management
Build Signing Ed25519 signing and verification
Guardrails Content filtering and PII detection

Operations

Document Description
Commands Full CLI reference
Configuration forge.yaml schema and environment variables
Dashboard Web UI features and architecture
Deployment Container packaging, Kubernetes, air-gap
Hooks Agent loop hook system
Plugins Framework plugin system
Command Integration Initializ Command platform guide

Philosophy

Running agents that do real work requires atomicity (explicit skills, defined tools, declared dependencies), security (restricted egress, encrypted secrets, audit trails), and portability (runs locally, in containers, in Kubernetes, in cloud — same agent, anywhere).

Real agent systems require atomicity, security, and portability. Forge provides those building blocks.

Contributing

We welcome contributions! See CONTRIBUTING.md for development setup, how to add skills/tools/channels, and the PR process.

Please read our Code of Conduct before participating.

License

See LICENSE for details.

Yorumlar (0)

Sonuc bulunamadi