{"id":45644470,"url":"https://github.com/initializ/forge","last_synced_at":"2026-05-26T05:00:35.170Z","repository":{"id":339915873,"uuid":"1163151015","full_name":"initializ/forge","owner":"initializ","description":"Forge is a secure, portable AI Agent runtime. Run agents locally, in cloud, or enterprise environments without exposing inbound tunnels.","archived":false,"fork":false,"pushed_at":"2026-03-01T07:39:39.000Z","size":1529,"stargazers_count":2,"open_issues_count":0,"forks_count":1,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-03-01T10:55:24.916Z","etag":null,"topics":["a2a","a2a-protocol","agent-cli","ai-agents","ai-agents-cli","ai-workforce","claude","enterprise-ai","llm-runtime","local-ai","local-ai-agents","mcp","openai","openclaw","portable-agents","secure-ai"],"latest_commit_sha":null,"homepage":"https://useforge.ai","language":"Go","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/initializ.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"docs/contributing.md","funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":"docs/security/SECURITY.md","support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2026-02-21T07:02:07.000Z","updated_at":"2026-03-01T07:33:13.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/initializ/forge","commit_stats":null,"previous_names":["initializ/forge"],"tags_count":4,"template":false,"template_full_name":null,"purl":"pkg:github/initializ/forge","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/initializ%2Fforge","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/initializ%2Fforge/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/initializ%2Fforge/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/initializ%2Fforge/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/initializ","download_url":"https://codeload.github.com/initializ/forge/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/initializ%2Fforge/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":30056056,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-03-03T18:21:05.932Z","status":"ssl_error","status_checked_at":"2026-03-03T18:20:59.341Z","response_time":61,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.5:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["a2a","a2a-protocol","agent-cli","ai-agents","ai-agents-cli","ai-workforce","claude","enterprise-ai","llm-runtime","local-ai","local-ai-agents","mcp","openai","openclaw","portable-agents","secure-ai"],"created_at":"2026-02-24T03:37:39.356Z","updated_at":"2026-05-26T05:00:35.153Z","avatar_url":"https://github.com/initializ.png","language":"Go","funding_links":[],"categories":[],"sub_categories":[],"readme":"\u003cp align=\"center\"\u003e\n  \u003cimg src=\"assets/banner.png\" alt=\"Forge — open-source AI agent framework\" width=\"100%\"\u003e\n\u003c/p\u003e\n\n# Forge — OpenClaw for Enterprise: A Secure, Portable AI Agent Runtime\n\n\u003cp align=\"center\"\u003e\n  \u003ca href=\"https://useforge.ai/docs/\"\u003e\u003cimg src=\"https://img.shields.io/badge/Docs-useforge.ai-FFD700?style=for-the-badge\" alt=\"Documentation\"\u003e\u003c/a\u003e\n  \u003ca href=\"https://discord.gg/PtFa4z97Ag\"\u003e\u003cimg src=\"https://img.shields.io/badge/Discord-5865F2?style=for-the-badge\u0026logo=discord\u0026logoColor=white\" alt=\"Discord\"\u003e\u003c/a\u003e\n  \u003ca href=\"https://github.com/initializ/forge/blob/main/LICENSE\"\u003e\u003cimg src=\"https://img.shields.io/badge/License-Apache%202.0-green?style=for-the-badge\" alt=\"License: Apache 2.0\"\u003e\u003c/a\u003e\n  \u003ca href=\"https://initializ.ai\"\u003e\u003cimg src=\"https://img.shields.io/badge/Built%20by-initializ-blueviolet?style=for-the-badge\" alt=\"Built by initializ\"\u003e\u003c/a\u003e\n\u003c/p\u003e\n\nBuild, run, and deploy AI agents from a single `SKILL.md` file.\nSecure by default. Runs anywhere — local, container, cloud, air-gapped.\n\n## Why Forge?\n\n- **60-second setup** — `forge init` wizard configures provider, keys, channels, and skills\n- **Secure by default** — outbound-only connections, egress allowlists, encrypted secrets, no public listeners\n- **Portable** — same agent runs locally, in Docker, Kubernetes, or inside [Initializ Command](https://initializ.ai)\n- **Observable** — structured NDJSON audit logs with correlation IDs for every action\n- **Extensible** — add skills, tools, channels, and LLM providers without changing core code\n\n## Quick Start\n\n```bash\n# Install (pick one)\nbrew install initializ/tap/forge\ncurl -sSL https://raw.githubusercontent.com/initializ/forge/main/install.sh | bash\n\n# Create and run an agent\nforge init my-agent \u0026\u0026 cd my-agent \u0026\u0026 forge run\n\n# Connect to Slack\nforge run --with slack\n```\n\nSee [Quick Start](docs/getting-started/quick-start.md) for the full walkthrough, or [Installation](docs/getting-started/installation.md) for all methods.\n\n## How It Works\n\n```\nSKILL.md --\u003e Parse --\u003e Discover tools/requirements --\u003e Compile AgentSpec\n                                                            |\n                                                            v\n                                                    Apply security policy\n                                                            |\n                                                            v\n                                                    Run LLM agent loop\n                                               (tool calling + memory + cron)\n```\n\nYou write a `SKILL.md`. Forge compiles it into a secure, runnable agent with egress controls, encrypted secrets, and audit logging.\n\n## Key Features\n\n| Feature | Description |\n|---------|-------------|\n| Atomic Skills | `SKILL.md`-based agent definitions with YAML frontmatter |\n| Egress Security | Runtime + build-time domain allowlists with subprocess proxy |\n| Channel Connectors | Slack (Socket Mode), Telegram (polling) — outbound-only |\n| Cron Scheduling | Recurring tasks with channel delivery |\n| Memory | Session persistence + long-term vector search |\n| LLM Fallbacks | Multi-provider with automatic failover |\n| MCP Client | Connect to any HTTP MCP server (Linear, Notion, Atlassian, ...) — tools surface as `\u003cserver\u003e__\u003ctool\u003e` with namespaced audit |\n| Web Dashboard | `forge ui` for browser-based agent management |\n| Build Signing | Ed25519 artifact signing \u0026 verification |\n| Air-Gap Ready | Runs with local models, no cloud required |\n\n## Documentation\n\n### Getting Started\n\n| Document | Description |\n|----------|-------------|\n| [Quick Start](docs/getting-started/quick-start.md) | Get an agent running in 60 seconds |\n| [Installation](docs/getting-started/installation.md) | Homebrew, binary, and Windows install |\n| [Architecture](docs/core-concepts/how-forge-works.md) | System design, module layout, and data flows |\n\n### Core Concepts\n\n| Document | Description |\n|----------|-------------|\n| [Skills](docs/skills/writing-custom-skills.md) | Skill definitions, registry, and compilation |\n| [Tools](docs/core-concepts/tools-and-builtins.md) | Built-in tools, adapters, and custom tools |\n| [Runtime](docs/core-concepts/runtime-engine.md) | LLM providers, fallback chains, running modes |\n| [Memory](docs/core-concepts/memory-system.md) | Session persistence and long-term memory |\n| [Channels](docs/core-concepts/channels.md) | Slack and Telegram adapter setup |\n| [Scheduling](docs/core-concepts/scheduling.md) | Cron configuration and schedule tools |\n\n### Security\n\n| Document | Description |\n|----------|-------------|\n| [Security Overview](docs/security/overview.md) | Complete security architecture |\n| [Authentication](docs/security/authentication.md) | Pluggable auth providers — OIDC, AWS Sigv4, GCP IAP, Azure AD |\n| [Egress Security](docs/security/egress-control.md) | Egress enforcement deep dive |\n| [Secrets](docs/security/secret-management.md) | Encrypted secret management |\n| [Build Signing](docs/security/build-signing.md) | Ed25519 signing and verification |\n| [Guardrails](docs/security/guardrails.md) | Content filtering and PII detection |\n\n### Operations\n\n| Document | Description |\n|----------|-------------|\n| [Commands](docs/reference/cli-reference.md) | Full CLI reference |\n| [Configuration](docs/reference/forge-yaml-schema.md) | `forge.yaml` schema and environment variables |\n| [Dashboard](docs/reference/web-dashboard.md) | Web UI features and architecture |\n| [Deployment](docs/deployment/kubernetes.md) | Container packaging, Kubernetes, air-gap |\n| [Hooks](docs/core-concepts/hooks.md) | Agent loop hook system |\n| [Plugins](docs/reference/framework-plugins.md) | Framework plugin system |\n| [Command Integration](docs/reference/command-integration.md) | Initializ Command platform guide |\n\n## Philosophy\n\nRunning 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).\n\n\u003e Real agent systems require atomicity, security, and portability. Forge provides those building blocks.\n\n## Contributing\n\nWe welcome contributions! See [CONTRIBUTING.md](CONTRIBUTING.md) for development setup, how to add skills/tools/channels, and the PR process.\n\nPlease read our [Code of Conduct](CODE_OF_CONDUCT.md) before participating.\n\n## License\n\nSee [LICENSE](LICENSE) for details.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Finitializ%2Fforge","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Finitializ%2Fforge","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Finitializ%2Fforge/lists"}