Development
Plugin
forge
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.
Plugin Signal71/100Solid
maintained99
capable29
documented100
adopted48
Install
$ npx -y skills add initializ/forge --agent claude-code
Run the curl in your terminal, the rest in Claude Code.
Stats
187
Stars
10
Forks
Active
Maintenance
Go
Language
Apache-2.0
License
1d ago
Last commit
5mo ago
Created
Repo: initializ/forge
What's inside
Skills
2Badges
4
README
1Forge — 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 initwizard 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
Talk to a working agent, and watch it use a tool, in under 60 seconds:
brew install initializ/tap/forge && forge try
forge try scaffolds a keyless demo agent, finds whatever model credential you
already have, and drops you into a chat whose every tool call and egress check
renders inline:
you › what's the weather in Tokyo, should I pack an umbrella?
▸ tool weather_current(location=Tokyo)
▸ egress wttr.in ✓ allowed
◂ 18C, light rain this evening
agent › 18C in Tokyo with light rain tonight. Yes, take the umbrella.
Then build your own: forge try --keep graduates the demo to ./forge-quickstart.
See Quick Start for the walkthrough, Ship to Production for the full pipeline, 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 |
| MCP Client | Connect to any HTTP MCP server (Linear, Notion, Atlassian, ...) — tools surface as <server>__<tool> 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 | Talk to an agent in 60 seconds with forge try |
| Ship to Production | The full init, build, package, deploy pipeline |
| Installation | Homebrew, binary, and Windows install |
| Architecture | System design, module layout, and data flows |
Core Concepts
| Document | Description |
|---|---|
| Skills | Skill definitions, registry, and compilation |
| Binary Dependencies | How forge build resolves, installs, and places skill-declared binaries |
| Tools | Built-in tools, adapters, and custom tools |
| Runtime | LLM providers, fallback chains, running modes |
| Memory | Session persistence and long-term memory |
| Context Compression | Reversible compression of bulky tool outputs — fewer tokens, nothing lost |
| Channels | Slack and Telegram adapter setup |
| Scheduling | Cron configuration and schedule tools |
| Tracing | OpenTelemetry distributed tracing — spans, propagation, audit cross-link |
Security
| Document | Description |
|---|---|
| Security Overview | Complete security architecture |
| Authentication | Pluggable auth providers — OIDC, AWS Sigv4, GCP IAP, Azure AD |
| Egress Security | Egress enforcement deep dive |
| Secrets | Encrypted secret management |
| Build Signing | Ed25519 signing and verification |
| Guardrails | Content filtering and PII detection |
| Workflow Correlation | Orchestrator correlation IDs threaded through audit events |
| Platform Policy | Workspace-level deploy-time bounds on egress / tools / models |
Operations
| Document | Description |
|---|---|
| A2A Agent Card | Spec-conformant Agent Card at /.well-known/agent-card.json (A2A 0.3.0) |
| Commands | Full CLI reference |
| Configuration | forge.yaml schema and environment variables |
| Dashboard | Web UI features and architecture |
| Deployment | Container packaging, Kubernetes, air-gap |
| Scheduler — Kubernetes | Hybrid file/CronJob scheduler backend, RBAC, token plumbing |
| Hooks | Agent loop hook system |
| Library Modules | Import forge-core, forge-skills, forge-plugins as Go libraries — tag scheme, release pipeline, embedder API |
| Plugins | Framework plugin system |
| Command Integration | Initializ Command platform guide |
For Claude / LLM-assisted contributors
| File | Description |
|---|---|
| Forge knowledge skill | 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 | 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 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.
File tree
1054initializ/forgeView on GitHub
.claude/
commands/
sync-docs.md
settings.json
skills/
forge-skill-builder.md
forge.md
.dockerignore
.github/
ISSUE_TEMPLATE/
bug-report.yml
config.yml
feature-request.yml
new-skill.yml
PULL_REQUEST_TEMPLATE.md
workflows/
ci.yaml
docs-links.yaml
edge.yaml
notify-docs.yaml
release.yaml
.gitignore
.goreleaser.yaml
assets/
banner.png
CHANGELOG.md
CLAUDE.md
CODE_OF_CONDUCT.md
CONTRIBUTING.md
Dockerfile
docs/
core-concepts/
binary-dependencies.md
channels.md
context-compression.md
hooks.md
how-forge-works.md
memory-system.md
observability-tracing.md
runtime-engine.md
scheduling.md
skill-md-format.md
tools-and-builtins.md
deployment/
docker.md
kubernetes.md
monitoring.md
production-checklist.md
scheduler-kubernetes.md
faq.md
getting-started/
configuration.md
contributing.md
installation.md
quick-start.md
ship-to-production.md
your-first-skill.md
mcp/
audit-events.md
cli-reference.md
configuration.md
delegated-consent.md
index.md
troubleshooting.md
reference/
a2a-agent-card.md
agent-skills-compatibility.md
browser-tools.md
cli-reference.md
command-integration.md
environment-variables.md
forge-yaml-schema.md
framework-plugins.md
library-modules.md
web-dashboard.md
security/
admission.md
audit-logging.md
audit-signing.md
audit-tamper-evidence.md
authentication.md
build-signing.md
defer-decisions.md
egress-control.md
guardrails.md
intent-alignment.md
least-privilege-credentials.md
overview.md
platform-policy.md
policy-decisions.md
secret-management.md
step-up-auth.md
tenancy.md
trust-model.md
workflow-correlation.md
skills/
contributing-a-skill.md
embedded-skills.md
skills-cli.md
writing-custom-skills.md
ui/
skill-builder-llm.md
examples/
platform-policy.yaml
forge-cli/
build/
agentspec_skills_test.go
agentspec_skills.go
agentspec_stage_test.go
agentspec_stage.go
channels_stage_test.go
channels_stage.go
dockerfile_stage_curl_test.go
dockerfile_stage_issue147_test.go
dockerfile_stage_test.go
dockerfile_stage.go
egress_stage_llm_test.go
egress_stage_otel_test.go
egress_stage_test.go
egress_stage.go
framework_adapter_stage_test.go
framework_adapter_stage.go
integration_test.go
k8s_stage_test.go
k8s_stage.go
manifest_stage_test.go
manifest_stage.go
model_provider_stage_test.go
model_provider_stage.go
network_policy_test.go
policy_stage.go
requirements_stage_browser_test.go
requirements_stage_test.go
requirements_stage.go
schedule_manifest_stage_test.go
schedule_manifest_stage.go
secret_safety_stage_test.go
secret_safety_stage.go
security_stage_issue145_test.go
security_stage_test.go
security_stage.go
signing_stage_test.go
signing_stage.go
skills_stage_browser_test.go
skills_stage_test.go
skills_stage.go
tool_filter_stage.go
tools_stage_test.go
tools_stage.go
validate_stage_test.go
validate_stage.go
channels/
config.go
env_test.go
env.go
integration_test.go
router_test.go
router.go
cmd/
audit_test.go
audit.go
auth_logout_test.go
auth_logout.go
auth_test.go
auth.go
build_test.go
build.go
channel_msteams_login.go
channel_test.go
channel.go
common.go
compression.go
export_test.go
export.go
forge/
main.go
guardrails_test.go
guardrails.go
init_auth_test.go
init_auth.go
init_custom_provider_test.go
init_egress.go
init_oneof_test.go
init_test.go
init_validate_test.go
init_validate.go
init.go
key.go
mcp_browser.go
mcp_cli_test.go
mcp_env_test.go
mcp_list.go
mcp_login.go
mcp_logout.go
mcp_test_cmd.go
mcp.go
package_test.go
package.go
root.go
run_test.go
run.go
schedule.go
secret.go
serve_test.go
serve_unix.go
serve_windows.go
serve.go
skill_env_test.go
skill_env.go
skills.go
tool_test.go
tool.go
try_test.go
try.go
ui_skill_save_test.go
ui_skill_save.go
ui.go
validate_test.go
validate.go
config/
forge_yaml.go
container/
buildah.go
builder_test.go
builder.go
docker_test.go
docker.go
manifest_test.go
manifest.go
podman.go
verify.go
go.mod
go.sum
internal/
devicecode/
devicecode.go
tryview/
renderer_test.go
renderer.go
tui/
banner.go
components/
egress_display.go
file_list.go
kbd_hint.go
multi_select_test.go
multi_select.go
secret_input.go
single_select.go
summary_box.go
text_input.go
messages.go
step.go
steps/
channel_step.go
compression_step_test.go
compression_step.go
egress_step.go
fallback_step.go
name_step.go
provider_step.go
reentry_test.go
review_step.go
skills_step.go
step_auth_test.go
step_auth.go
web_search_step_test.go
web_search_step.go
theme.go
wizard_nav_test.go
wizard.go
plugins/
crewai/
crewai_test.go
crewai.go
custom/
custom_test.go
custom.go
langchain/
langchain_test.go
langchain.go
runtime/
admission_engine_test.go
admission_engine.go
admission_loader.go
agentcard.go
audit_capture_resolver_test.go
audit_capture_resolver.go
audit_payload_capture_hook_test.go
audit_tool_exec_seq_test.go
auth_audit_seq_test.go
auth_audit_test.go
auth_chain_test.go
auth_config_test.go
banner_version_test.go
credentials_audit.go
defer_test.go
defer.go
env_test.go
env.go
file_tools_register_test.go
forge_usage_headers_test.go
forge_usage_headers.go
guardrails_audit.go
guardrails_engine_test.go
guardrails_engine.go
guardrails_loader_test.go
guardrails_loader.go
guardrails_merge_test.go
guardrails_merge.go
guardrails_overlay_test.go
guardrails_overlay.go
guardrails_tracing_test.go
guardrails_tracing.go
ingress_context_middleware.go
intent_alignment_test.go
intent_alignment.go
intent_drift_test.go
jwks_endpoint_test.go
local_session_test.go
local_session.go
mcp_authgate_test.go
mcp_authgate.go
mcp_consent_callback_test.go
mcp_consent_callback.go
mcp_standalone_consent_test.go
mcp_standalone_consent.go
mock_executor_test.go
mock_executor.go
mock_test.go
mock.go
platform_command_guard_test.go
rate_limit_test.go
rate_limit.go
runner_agentcard_audit.go
runner_agentcard_skills_test.go
runner_agentcard_skills.go
runner_browser_test.go
runner_browser.go
runner_compression_test.go
runner_jsonrpc_headers_test.go
runner_mcp_e2e_test.go
runner_mcp_nits_test.go
runner_mcp_test.go
runner_mcp.go
runner_message_validation_test.go
runner_oauth_guardrail_test.go
runner_secrets_test.go
runner_skill_catalog_test.go
runner_test.go
runner.go
scheduler_k8s_backend_test.go
scheduler_k8s_backend.go
scheduler_store_test.go
scheduler_store.go
seq_registry_wiring_test.go
session_store_loader_test.go
session_store_loader.go
step_up_execute_task_test.go
step_up_test.go
step_up.go
stub_executor_test.go
stub_executor.go
subprocess_executor_test.go
subprocess_executor.go
subprocess_test.go
subprocess.go
tracing_resolve_test.go
tracing_resolve.go
tracing_runner_test.go
verify_issue147_test.go
verify_test.go
verify.go
watcher_test.go
watcher.go
server/
a2a_server_agentcard_test.go
a2a_server_propagation_test.go
a2a_server_ratelimit_test.go
a2a_server_response_header_test.go
a2a_server_spans_test.go
a2a_server_test.go
a2a_server_workflow_test.go
a2a_server.go
admission_middleware_test.go
admission_middleware.go
response_header_stage_test.go
response_header_stage.go
skills/
loader.go
templates/
deployment.yaml.tmpl
docker-compose.yaml.tmpl
Dockerfile.tmpl
embed.go
init/
crewai/
agent.py.tmpl
example_tool.py.tmpl
custom/
... 804 moreFAQ
forge is a Claude Code plugin with 2 hand-picked skills for development work, indexed on Flowy. Install it with the command on its page. It includes code-agent, k8s-incident-triage. Its skills do not fire on their own yet. Request auto-invocation to have Flowy route them as you prompt. Free and open source.
- What is forge?
- 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.
- How do I install forge?
- Run these in Claude Code: npx -y skills add initializ/forge --agent claude-code. Then prompt normally.
- Does forge auto-invoke its skills?
- Not yet. It is indexed on Flowy as a plain plugin. Request auto-invocation on its page and Flowy will route its skills for you as you prompt.
- Is forge free?
- Yes. Flowy is free and open source, with nothing gated. You can read every skill in full before you install.