Forge

Forge — An Open, Secure, Portable AI Agent Runtime for the Enterprise

Forge is the open-source runtime for Anthropic's Agent Skills standard — built for the agent that runs next to a service, in your environment, on infrastructure you already operate. Write a SKILL.md. Compile to a portable, hardened agent. Deploy it anywhere containers run: Kubernetes, on-prem, air-gapped, embedded in CI, or as an A2A endpoint.

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](docs/getting-started/quick-start.md) for the full walkthrough, or [Installation](docs/getting-started/installation.md) 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 | | MCP Client | Connect to any HTTP MCP server (Linear, Notion, Atlassian, ...) — tools surface as __ with namespaced audit | | 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](docs/getting-started/quick-start.md) | Get an agent running in 60 seconds | | [Installation](docs/getting-started/installation.md) | Homebrew, binary, and Windows install | | [Architecture](docs/core-concepts/how-forge-works.md) | System design, module layout, and data flows |

Core Concepts

| Document | Description | |----------|-------------| | [Skills](docs/skills/writing-custom-skills.md) | Skill definitions, registry, and compilation | | [Binary Dependencies](docs/core-concepts/binary-dependencies.md) | How forge build resolves, installs, and places skill-declared binaries | | [Tools](docs/core-concepts/tools-and-builtins.md) | Built-in tools, adapters, and custom tools | | [Runtime](docs/core-concepts/runtime-engine.md) | LLM providers, fallback chains, running modes | | [Memory](docs/core-concepts/memory-system.md) | Session persistence and long-term memory | | [Context Compression](docs/core-concepts/context-compression.md) | Reversible compression of bulky tool outputs — fewer tokens, nothing lost | | [Channels](docs/core-concepts/channels.md) | Slack and Telegram adapter setup | | [Scheduling](docs/core-concepts/scheduling.md) | Cron configuration and schedule tools | | [Tracing](docs/core-concepts/observability-tracing.md) | OpenTelemetry distributed tracing — spans, propagation, audit cross-link |

Security

| Document | Description | |----------|-------------| | [Security Overview](docs/security/overview.md) | Complete security architecture | | [Authentication](docs/security/authentication.md) | Pluggable auth providers — OIDC, AWS Sigv4, GCP IAP, Azure AD | | [Egress Security](docs/security/egress-control.md) | Egress enforcement deep dive | | [Secrets](docs/security/secret-management.md) | Encrypted secret management | | [Build Signing](docs/security/build-signing.md) | Ed25519 signing and verification | | [Guardrails](docs/security/guardrails.md) | Content filtering and PII detection | | [Workflow Correlation](docs/security/workflow-correlation.md) | Orchestrator correlation IDs threaded through audit events | | [Platform Policy](docs/security/platform-policy.md) | Workspace-level deploy-time bounds on egress / tools / models |

Operations

| Document | Description | |----------|-------------| | [A2A Agent Card](docs/reference/a2a-agent-card.md) | Spec-conformant Agent Card at /.well-known/agent-card.json (A2A 0.3.0) | | [Commands](docs/reference/cli-reference.md) | Full CLI reference | | [Configuration](docs/reference/forge-yaml-schema.md) | forge.yaml schema and environment variables | | [Dashboard](docs/reference/web-dashboard.md) | Web UI features and architecture | | [Deployment](docs/deployment/kubernetes.md) | Container packaging, Kubernetes, air-gap | | [Scheduler — Kubernetes](docs/deployment/scheduler-kubernetes.md) | Hybrid file/CronJob scheduler backend, RBAC, token plumbing | | [Hooks](docs/core-concepts/hooks.md) | Agent loop hook system | | [Library Modules](docs/reference/library-modules.md) | Import forge-core, forge-skills, forge-plugins as Go libraries — tag scheme, release pipeline, embedder API | | [Plugins](docs/reference/framework-plugins.md) | Framework plugin system | | [Command Integration](docs/reference/command-integration.md) | Initializ Command platform guide |

For Claude / LLM-assisted contributors

| File | Description | |------|-------------| | [Forge knowledge skill](.claude/skills/forge.md) | Single comprehensive markdown — drop it into a Claude conversation for full Forge context (architecture, security, APIs, CLI, audit pipeline, how to build agents + skills). | | [Forge skill-builder skill](.claude/skills/forge-skill-builder.md) | Same prompt the forge ui Skill Builder uses. Author a valid SKILL.md (frontmatter + body + optional scripts) in any Claude chat — no forge ui needed. |

/sync-docs keeps both skills current — see .claude/commands/sync-docs.md.

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](CONTRIBUTING.md) for development setup, how to add skills/tools/channels, and the PR process.

Please read our [Code of Conduct](CODEOFCONDUCT.md) before participating.

License

See [LICENSE](LICENSE) for details.

Source & license

This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code.

• Author: initializ
• Source: initializ/forge
• License: Apache-2.0
• Homepage: https://go.useforge.ai/launch?ref=github

Install and usage instructions live in the source repository linked above.