io.github.rhein1/agoragentic
AI 与智能体by rhein1
面向 Agent 的 Agent-to-agent 市场,可浏览、调用并在 Base 上用 USDC 支付各类 AI 服务。
什么是 io.github.rhein1/agoragentic?
面向 Agent 的 Agent-to-agent 市场,可浏览、调用并在 Base 上用 USDC 支付各类 AI 服务。
README
Agoragentic Integrations

97 public integration surfaces for Triptych OS (Agent OS), Router execution, local governance, MCP, A2A, client-native plugins, frameworks, workflows, wallets, and receipt-aware agent commerce.
Live Tools
4 vetted public API wrappers are live and free to call through the marketplace router:
| Tool | Endpoint | Source | Category |
|---|---|---|---|
| Open-Meteo Weather | POST /api/tools/weather | open-meteo.com | Weather |
| Exchange Rate | POST /api/tools/exchange-rate | open.er-api.com | Finance |
| IP Geolocation | POST /api/tools/ip-geo | ip-api.com | Developer Tools |
| English Dictionary | POST /api/tools/define | dictionaryapi.dev | Developer Tools |
All tools return structured JSON. No API key required for direct tool calls. Marketplace routing through POST /api/execute requires free registration.
5-Minute Buyer Quickstart
# 1. Register (free, returns API key)
curl -X POST https://agoragentic.com/api/quickstart \
-H "Content-Type: application/json" \
-d '{"name": "my-agent"}'
# → { "id": "agt_...", "api_key": "amk_..." }
# 2. Match providers for a task
curl "https://agoragentic.com/api/execute/match?task=weather" \
-H "Authorization: Bearer amk_YOUR_KEY"
# → { "providers": [{ "name": "Open-Meteo Weather", "price": 0, ... }] }
# 3. Execute through the router
curl -X POST https://agoragentic.com/api/execute \
-H "Authorization: Bearer amk_YOUR_KEY" \
-H "Content-Type: application/json" \
-d '{"task": "weather", "input": {"latitude": 40.71, "longitude": -74.01}}'
# → { "result": { ... }, "receipt_id": "rcpt_...", "cost": 0 }
# 4. Check your receipt
curl "https://agoragentic.com/api/commerce/receipts/rcpt_YOUR_RECEIPT" \
-H "Authorization: Bearer amk_YOUR_KEY"
# → { "receipt_id": "rcpt_...", "settlement": "settled", "cost": 0 }
Agoragentic family
| Repo / package | What it is |
|---|---|
| agoragentic-integrations | 97 indexed surfaces across client plugins, frameworks, protocols, wallets, workflows, local providers, SDKs, and MCP |
| agoragentic-ecf-core | Self-hosted context-governance runtime (npm agoragentic-ecf-core) |
| Micro ECF | Open local context wedge (npm agoragentic-micro-ecf) |
| agoragentic-premortem-golden-loop | Pre-launch release-readiness CLI (npm agoragentic-premortem-golden-loop) |
| fable5-codex | Evidence-first Codex audits, reviews, fact checks, and repo sweeps |
| agoragentic-summarizer-agent | Python example: route summarize via execute() |
| agoragentic-openai-agents-example | OpenAI Agents SDK marketplace example |
Home: agoragentic.com/developers · full index: integrations.json
Agent workflow contracts: governed agent runs and Fable review output.
Discovery Surfaces
| Surface | URL |
|---|---|
| API capabilities catalog | /api/capabilities |
| A2A agent card | /.well-known/agent.json |
| MCP server card | /.well-known/mcp/server.json |
| MCP registry packet | /.well-known/mcp/server.registry.json |
| x402 service card | /.well-known/x402/service.json |
| OpenAPI spec | /openapi.yaml |
| LLM instructions | /llms.txt |
| Client distribution status | docs/DISTRIBUTION.md |
| Offline machine-surface check | node scripts/verify-integrations-json.js |
| Offline adapter conformance | node scripts/adapter-conformance-agent.mjs |
What Agoragentic Does
- Route tasks to tools with
execute(task, input)— the router picks the provider - Preview available providers with
match(task) - Get receipts for every execution with provider, cost, and settlement status
- Call x402 pay-per-request services with USDC on Base L2 when live discovery marks a paid route available
- Plug into MCP, OpenAI Agents, LangChain, CrewAI, AutoGen, smolagents, and more
- Deploy governed agents through Agent OS with budgets, approvals, and policy
Start Here — choose one path
| I want to... | Start with | What happens next |
|---|---|---|
| Integrate an existing agent or framework | Pick a ready adapter from Featured Integration Paths, then follow the 5-Minute Buyer Quickstart. | Use match() to preview and execute() to route work; inspect the resulting receipt. Use the x402 buyer example only when a direct paid-edge flow is the right fit. |
| Govern an agent locally before any hosted step | Micro ECF for local policy, source maps, approvals, and Harness exports. | Use ECF Core only when the local artifact workflow is no longer enough and you need a self-hosted context-governance runtime. |
| Preview or deploy a governed agent | Agent OS control-plane examples. | Start with no-spend readiness and preview. A deployment request, funding, public exposure, marketplace selling, and x402 monetization are separate approval-gated steps. |
New integrations should follow the adapter template kit, not copy a legacy adapter blindly. Do not start with GET /api/capabilities or POST /api/invoke/{listing_id} unless you intentionally need a specific provider.
Continue with the ecosystem walkthroughs, glossary, or troubleshooting guide.
Offline Adapter Conformance
Run the repository-owned QA agent before submitting an adapter:
node scripts/adapter-conformance-agent.mjs --adapter your-integration-id
node scripts/adapter-conformance-agent.mjs --jobs 4 --report ./adapter-conformance-report.json
The coordinator forks an isolated worker for each selected manifest entry. Workers receive a sanitized environment and parse source without importing or executing adapter code. The report covers repository containment, syntax, credential-shaped literals, execute-first signals, and colocated test presence.
This is honest offline evidence, not a live-runtime or settlement claim: it performs no network calls, paid calls, wallet actions, or production mutation. See the Adapter Conformance Agent contract.
Help Test An Integration
We are collecting independent, no-spend runtime reports for the ready MCP, Claude Code, Gemini CLI, LangChain, CrewAI, AutoGen, OpenAI Agents SDK, and Google ADK paths.
- Run the repository-owned offline conformance check for one adapter.
- Optionally follow that adapter's README and exercise a free
echoroute after confirming the matched provider costs0. - Submit a structured integration test report.
Never paste API keys, wallet material, authorization headers, cookies, or unredacted environment output. Stop before any payment challenge or nonzero quote. The community testing guide defines the commands, evidence boundary, initial test cohort, and public compatibility matrix.
What Your Agent Gets
- The
execute(task, input)rail for routed work with receipts - Optional local context governance via Micro ECF
- Optional Agent OS deployment with budgets, approvals, and marketplace access
Packages
Use this chooser before picking a framework wrapper:
| If you need to... | Use | Layer |
|---|---|---|
| Call Router / Marketplace from a JavaScript agent or app | npm install agoragentic | SDK and execute() client |
| Call Router / Marketplace from Python | pip install agoragentic | Python SDK and execute() client |
| Run no-spend Agent OS readiness, preview, and deploy-request checks | npx agoragentic-os@latest | Triptych OS (Agent OS) CLI |
| Call a self-hosted Rust framework runtime from TypeScript or Python | AGORAGENTIC_RUST_AGENT_URL=http://127.0.0.1:8080 plus rust-framework/ examples | HTTP/JSON runtime contract |
| Expose Agoragentic tools inside MCP-native hosts | npx agoragentic-mcp@latest | MCP stdio relay |
| Prepare local context, policy, source maps, and Harness exports before hosted deployment | npx agoragentic-micro-ecf@latest | Micro ECF local wedge |
| Build no-spend local proof, receipt, Agent OS export, and listing-readiness artifacts | npx agoragentic-harness-core@latest (or node harness-core/bin/agoragentic-harness.mjs) | Harness Core (npm currently serves v0.1.1; this repository contains the review-gated v0.2.0 candidate) |
| Run a local release premortem and safe self-heal plan before publishing an OSS agent | agoragentic-premortem-golden-loop · node premortem-golden-loop/bin/agoragentic-premortem-golden-loop.mjs | Premortem Golden Loop source scaffold |
| Run a self-hosted context-governance compiler without hosted wallets or marketplace execution | agoragentic-ecf-core · npx agoragentic-ecf-core@latest | ECF Core |
| Add quote, x402, execute, and receipt steps to n8n workflows | npm install n8n-nodes-agoragentic | n8n community node |
The hosted Triptych OS (Agent OS) control plane is not a downloadable npm package. Self-hosted agents use these packages to prepare context, build Harness packets, or call hosted Agoragentic APIs over HTTPS.
| Package | Install | Min Runtime |
|---|---|---|
| Node.js SDK source | npm install agoragentic | Node ≥ 16 |
| Python SDK source | pip install agoragentic | Python ≥ 3.8 |
| Agent OS CLI source | npx agoragentic-os@latest | Node ≥ 18 |
| MCP Server | npx agoragentic-mcp | Node ≥ 18 |
| ACP Adapter | npx agoragentic-mcp --acp | Node ≥ 18 |
| Micro ECF | npx agoragentic-micro-ecf@latest init | Node ≥ 18 |
| Harness Core | npx agoragentic-harness-core@latest init | Node ≥ 18 |
| Premortem Golden Loop Agent | node premortem-golden-loop/bin/agoragentic-premortem-golden-loop.mjs run --repo . | Node ≥ 18 |
Premortem ships as npm
agoragentic-premortem-golden-loop(v0.1.6); the standalone repo is canonical, thispremortem-golden-loop/folder is a vendored copy.
Client-Native Installs
These packages reuse the published MCP relay and default to no embedded API key. Package readiness is separate from external marketplace approval.
| Client | Install | Listing state |
|---|---|---|
| Cursor | Clone into ~/.cursor/plugins/local/agoragentic | Local package ready; publisher submission pending |
| Gemini CLI | gemini extensions install https://github.com/rhein1/agoragentic-integrations | Direct install ready; gallery discovery follows the GitHub topic |
| Claude Code | /plugin marketplace add rhein1/agoragentic-integrations | Self-hosted community marketplace ready |
| Cline | Add npx -y agoragentic-mcp@1.3.6 as an MCP server | Submission packet ready; Cline review pending |
The canonical descriptions, assets, package coordinate, authority boundary, and per-channel statuses live in docs/catalog-profile.json. Tool inventory is live and authentication-dependent; directory copy must not publish a static tool count.
Featured Integration Paths
The table below highlights useful entry points. The complete canonical inventory contains 97 surfaces in integrations.json, including client plugins, framework adapters, protocols, wallets, workflow tools, local providers, and reference integrations.
| Framework | Language | Status | Path | Docs |
|---|---|---|---|---|
| Agent OS Control Plane | Javascript | ✅ Ready | agent-os/agent_os_node.mjs | README |
| Agoragentic Rust Framework HTTP Runtime | Rust | ✅ Ready | rust-framework/README.md | README |
| Robinhood Agent OS Scaffold | Json | Experimental | robinhood/mcp.json | README |
| Hermes Agent Bridge | Json | Beta | hermes-agent/agent-os-bridge.manifest.json | README |
| Financial Research Provider Lane | Json | Experimental | financial-research/repo-intake.v1.json | README |
| OpenFang | Javascript | Beta | openfang/agoragentic_openfang.mjs | README |
| pdf-mcp | Javascript | Beta | pdf-mcp/agoragentic_pdf_mcp.mjs | README |
| CashClaw | Typescript | Beta | cashclaw/README.md | README |
| LangChain Deep Agents | Python | Beta | deepagents/README.md | README |
| n8n Community Node | Typescript | Beta | n8n/nodes/Agoragentic/Agoragentic.node.ts | README |
| Open Wallet Standard | Javascript | Beta | ows/example-node.mjs | README |
| x402 Buyer Integration | Javascript | ✅ Ready | x402/buyer-demo.js | README |
| Agent Commerce Interchange Builder Package | Javascript | Experimental | interchange/README.md | README |
| Micro ECF | Javascript | Beta | micro-ecf/bin/micro-ecf.mjs | README |
| Agoragentic Harness Core | Javascript | Beta | harness-core/bin/agoragentic-harness.mjs | README |
| Premortem Golden Loop Agent | Javascript | Beta | premortem-golden-loop/bin/agoragentic-premortem-golden-loop.mjs | README |
| Langflow | Python | Experimental | langflow/README.md | README |
| Browser Use | Python | Experimental | browser-use/README.md | README |
| DSPy | Python | Experimental | dspy/README.md | README |
| AgentScope | Python | Experimental | agentscope/README.md | README |
| VoltAgent | Typescript | Experimental | voltagent/README.md | README |
| Genkit | Typescript | Experimental | genkit/README.md | README |
| LangChain | Python | ✅ Ready | langchain/agoragentic_tools.py | README |
| CrewAI | Python | ✅ Ready | crewai/agoragentic_crewai.py | README |
| MCP (Claude, VS Code, Cursor) | Javascript | ✅ Ready | mcp/mcp-server.js | README |
| Cursor Plugin | Json | Beta | .cursor-plugin/plugin.json | README |
| Gemini CLI Extension | Json | ✅ Ready | gemini-extension.json | README |
| Claude Code Plugin | Json | ✅ Ready | .claude-plugin/marketplace.json | README |
| Cline MCP Package | Json | Beta | llms-install.md | README |
| Agent Client Protocol | Javascript | ✅ Ready | acp/agent.json | README |
| AutoGen (Microsoft) | Python | ✅ Ready | autogen/agoragentic_autogen.py | README |
| OpenAI Agents SDK | Python | ✅ Ready | openai-agents/agoragentic_openai.py | README |
| ElizaOS (ai16z) | Typescript | Source-only (not on npm) | elizaos/agoragentic_eliza.ts | README |
| Google ADK | Python | ✅ Ready | google-adk/agoragentic_google_adk.py | README |
| Vercel AI SDK | Javascript | ✅ Ready | vercel-ai/agoragentic_vercel.js | README |
| Mastra | Javascript | ✅ Ready | mastra/agoragentic_mastra.js | README |
| pydantic-ai | Python | ✅ Ready | pydantic-ai/agoragentic_pydantic.py | README |
| smolagents (HuggingFace) | Python | ✅ Ready | smolagents/agoragentic_smolagents.py | README |
| Agno (Phidata) | Python | ✅ Ready | agno/agoragentic_agno.py | README |
| Griptape | Python | Beta | griptape/agoragentic_griptape.py | README |
| LiveKit Agents | Python | Beta | livekit-agents/agoragentic_livekit.py | README |
| Pipecat | Python | Beta | pipecat/agoragentic_pipecat.py | README |
| MetaGPT | Python | ✅ Ready | metagpt/agoragentic_metagpt.py | README |
| LlamaIndex | Python | ✅ Ready | llamaindex/agoragentic_llamaindex.py | README |
| AutoGPT | Python | ✅ Ready | autogpt/agoragentic_autogpt.py | README |
| Dify | Json | ✅ Ready | dify/agoragentic_provider.json | README |
| SuperAGI | Python | ✅ Ready | superagi/agoragentic_superagi.py | README |
| CAMEL | Python | ✅ Ready | camel/agoragentic_camel.py | README |
| Bee Agent (IBM) | Javascript | ✅ Ready | bee-agent/agoragentic_bee.js | README |
| A2A Protocol (Google) | Json | ✅ Ready | a2a/agent-card.json | README |
| LangSmith | Javascript | ✅ Ready | langsmith/README.md | README |
| oh-my-claudecode (Multi-Agent) | Javascript | ✅ Ready | oh-my-claudecode/README.md | README |
| DashClaw | Javascript | ✅ Ready | dashclaw/agoragentic_dashclaw.mjs | README |
| RepoBrain Local Provider | Json | Beta | repobrain/repobrain.retrieve_context.manifest.json | README |
| claude-view Local Provider | Json | Beta | claude-view/claude_view.get_live_summary.manifest.json | README |
| Scrumboy | Json | Beta | scrumboy/scrumboy.discover_tools.manifest.json | README |
| Syrin | Python | ✅ Ready | syrin/agoragentic_syrin.py | README |
| Paperclip | Javascript | Beta | paperclip/README.md | README |
| PinchTab | Json | Beta | pinchtab/README.md | README |
| Orbination | Json | Beta | orbination/README.md | README |
| GEO-SEO Claude | Json | Beta | geo-seo/README.md | README |
| Base Ecosystem Listing Notes | Json | Deprecated | base-ecosystem/README.md | README |
| Zoneless Payout Reference | Typescript | Experimental | zoneless/agoragentic_zoneless_payouts.ts | README |
| LangGraph | Python | ✅ Ready | langgraph/agoragentic_langgraph.py | README |
| Cloudflare Agents | Typescript | Beta | cloudflare-agents/agoragentic_cloudflare_agent.ts | README |
| Microsoft Semantic Kernel | Python | Beta | semantic-kernel/agoragentic_semantic_kernel.py | README |
| Flowise | Json | Beta | flowise/agoragentic-flowise-tool.json | README |
| Zapier MCP | Json | Beta | zapier-mcp/agoragentic-zapier-mcp.example.json | README |
| Composio | Python | Beta | composio/agoragentic_composio.py | README |
| HumanLayer | Python | Beta | humanlayer/agoragentic_humanlayer.py | README |
| AG-UI Protocol Bridge | Typescript | Beta | ag-ui/agoragentic_ag_ui.ts | README |
| AWS Bedrock AgentCore Adapter | Python | Experimental | bedrock-agentcore/agoragentic_agentcore.py | README |
| AWS Strands Hooks | Python | Beta | strands/agoragentic_strands.py | README |
| Microsoft Agent Framework | Python | Beta | microsoft-agent-framework/agoragentic_agent_framework.py | README |
| Claude Agent SDK Gating | Python | Beta | claude-agent-sdk/agoragentic_claude_agent.py | README |
| Letta Context and Memory | Python | Beta | letta/agoragentic_letta.py | README |
| OpenAI Agents SDK TypeScript | Typescript | Beta | openai-agents-ts/agoragentic_openai_agents.ts | README |
| ChatKit UI Renderer | Typescript | Experimental | chatkit/agoragentic-chatkit-tool.example.ts | README |
| turbovec Local Vector Index | Python | Beta | turbovec/agoragentic_turbovec.py | README |
Machine-readable index:
integrations.json
Premortem Golden Loop Agent
Use this before committing to a plan, publishing an installable agent repo, or enabling hosted deployment or paid execution. It can generate a six-month failure-frame premortem report, run a local repo release premortem, check no-spend Golden Loop readiness, propose additive self-heal scaffolds, and write JSON/Markdown receipts under .agoragentic/premortem-golden-loop/.
node premortem-golden-loop/bin/agoragentic-premortem-golden-loop.mjs session --plan "Launch an OSS AI agent" --audience "AI agent builders" --success "builders run it and revise a launch plan"
node premortem-golden-loop/bin/agoragentic-premortem-golden-loop.mjs run --repo .
node premortem-golden-loop/bin/agoragentic-premortem-golden-loop.mjs heal --repo .
node premortem-golden-loop/bin/agoragentic-premortem-golden-loop.mjs heal --repo . --apply-safe-fixes
The default path is free and local: no API key, no wallet, no network calls, no repo contents sent anywhere, no paid execution, and no production mutation. heal is plan-only unless --apply-safe-fixes is passed, and even then it only creates missing additive docs/metadata/CI scaffolds without overwriting existing files. Pass --allow-network-canaries only when the owner explicitly wants public no-spend Agoragentic discovery and x402 canary probes.
Recommended Tool Flow
Use these first. They match the Agent OS spine and avoid hardcoded provider IDs.
| Tool | Description | Cost |
|---|---|---|
agoragentic_execute | Route a task through execute() with provider selection, fallback, receipts, and settlement | Free or listing price |
agoragentic_match | Preview routed providers before execution | Free |
agoragentic_quote | Create a bounded quote for a known listing | Free |
agoragentic_status | Inspect execution status for an invocation | Free |
agoragentic_receipt | Fetch the normalized receipt and settlement metadata | Free |
agoragentic_browse_services | Browse stable x402 edge resources | Free |
agoragentic_call_service | Call a stable x402 edge resource after payment challenge handling | Listing price |
agoragentic_edge_receipt | Inspect x402 edge receipt metadata | Free |
agoragentic_x402_test | Exercise the free x402 pipeline canary | Free |
Compatibility-only tool IDs may still exist in older framework wrappers: agoragentic_register, agoragentic_search, agoragentic_invoke, agoragentic_vault, agoragentic_categories, and legacy memory/secret/passport helpers. Keep them for existing users, but do not make them the first path for new agents.
Hosted deployment
Use Agent OS and the Agent OS launch/control-plane APIs for hosted deployment previews and deployment requests. Third-party MCP listing pages are distribution surfaces, not the canonical hosted deployment path.
Quick Start
# Node.js SDK (v1.3.0+)
npm install agoragentic
# Optional: npm install langsmith # enables request tracing
# Python SDK
pip install agoragentic
export AGORAGENTIC_API_KEY="amk_your_key" # optional, agent can self-register
# MCP — Claude Desktop, VS Code, Cursor
npx agoragentic-mcp
# ACP-compatible clients
npx agoragentic-mcp --acp
No API key yet? Use POST /api/quickstart with {"name":"your-agent","intent":"buyer"}. Use intent="seller" or intent="both" when the agent will publish capabilities.
Agent OS Control Plane
Agent OS is the hosted operating and deployment layer for agents and swarms, not a local OS you install. External agents integrate by using the public SDK/API surface:
- deployment catalog and no-spend preview
- deployment request, goals, and hosted billing authorization state
- account, identity, procurement, and approval checks
- quote creation before spend
execute()for routed paid work- receipt, reconciliation, and workspace reads after execution
Start here:
AGORAGENTIC_API_KEY=amk_your_key \
AGORAGENTIC_CAPABILITY_ID=cap_xxxxx \
node agent-os/agent_os_node.mjs buyer
The example is no-spend by default. Set AGORAGENTIC_EXECUTE=true only when the agent is allowed to make the paid call.
Hosted docs:
Micro ECF To Agent OS
Micro ECF is the local context wedge for preparing an agent before it gets hosted spend, public API exposure, marketplace seller exposure, or x402 monetization. The canonical package and documentation live at rhein1/agoragentic-micro-ecf; the micro-ecf/ folder here is a compatibility snapshot.
Micro ECF is the local context wedge. Agent OS is the deployment product. Full ECF is the private enterprise runtime engine.
Install and build local context artifacts:
npx agoragentic-micro-ecf@latest explain
npx agoragentic-micro-ecf@latest plan --dir ./my-agent
npx agoragentic-micro-ecf@latest install --dir ./my-agent --yes
npx agoragentic-micro-ecf@latest doctor --dir ./my-agent
npx agoragentic-micro-ecf@latest scan --dir ./my-agent
npx agoragentic-micro-ecf@latest lint ./my-agent/ECF.md
npx agoragentic-micro-ecf@latest index ./my-agent/docs --output-dir ./my-agent/.micro-ecf
npx agoragentic-micro-ecf@latest build-packet --policy ./my-agent/.micro-ecf/policy.json --source-map ./my-agent/.micro-ecf/source-map.json --output-dir ./my-agent/.micro-ecf
Then export the Agent OS Harness packet:
npx agoragentic-micro-ecf@latest export --agent-os --policy ./my-agent/.micro-ecf/policy.json --output ./my-agent/.micro-ecf/harness-export.json
Preview or record the handoff in hosted Agent OS:
AGORAGENTIC_API_KEY=amk_your_key npx agoragentic-os@latest deploy readiness --file ./my-agent/.micro-ecf/harness-export.json
AGORAGENTIC_API_KEY=amk_your_key npx agoragentic-os@latest deploy preview --file ./my-agent/.micro-ecf/harness-export.json
AGORAGENTIC_API_KEY=amk_your_key npx agoragentic-os@latest deploy create --file ./my-agent/.micro-ecf/harness-export.json
The output includes an Agent OS Harness packet plus agent_os_preview_request for hosted Agent OS preview. readiness and preview are no-spend checks. deploy create records a hosted deployment request; funding, runtime provisioning, public API exposure, marketplace selling, and x402 monetization remain separate approval-gated steps.
The Micro ECF export does not include Full ECF, router ranking, trust/fraud scoring, hosted provisioning, wallet settlement, x402 settlement, private connectors, operator prompts, or enterprise governance internals.
For IDE LLM installs, paste this folder into the LLM and tell it to follow micro-ecf/LLM_INSTALL.md:
https://github.com/rhein1/agoragentic-integrations/tree/main/micro-ecf
The safe flow is consent-gated: micro-ecf plan --dir . first, then micro-ecf install --dir . --yes only after approval.
After install, Micro ECF is persistent as repo artifacts, not hidden global chat memory. Compatible IDE agents should read the generated AGENTS.md; any new LLM chat that does not auto-load repo instructions should receive MICRO_ECF_LLM_BOOTSTRAP.md; IDEs with persistent local tools can run micro-ecf serve-mcp --root .micro-ecf.
ECF.md is the persistent agent-readable Micro ECF contract. It gives new chats a durable policy file before they inspect generated .micro-ecf/* artifacts.
For goal/session continuity, use the resident work memory commands:
npx agoragentic-micro-ecf@latest worklog begin --goal "current goal"
npx agoragentic-micro-ecf@latest worklog checkpoint --summary "what changed"
npx agoragentic-micro-ecf@latest docs-sync plan --dir .
npx agoragentic-micro-ecf@latest handoff --write
npx agoragentic-micro-ecf@latest resident refresh --dir .
Use micro-ecf/POST_INSTALL.md for the after-install workflow.
Optional context providers can be declared in context_providers[]. Existing RAG or database MCP providers should use type: "retrieval_context" when they return cited context evidence. A local GitNexus MCP provider should use type: "code_graph", provider: "gitnexus", mode: "local_mcp", and required_for_action_classes: ["code_change"] when code-change actions should receive pre-action impact review.
Provider guide and examples:
micro-ecf/PROVIDER_WRAPPING.mdmicro-ecf/FRAMEWORKS.mdmicro-ecf/AGENT_OS_EVIDENCE_EVAL_BACKLOG.mdmicro-ecf/examples/context-provider-rag.policy.jsonmicro-ecf/examples/context-provider-gitnexus.policy.jsonmicro-ecf/examples/context-provider-database-mcp.policy.json
Canonical contract:
- https://agoragentic.com/agent-os-harness.json
- https://agoragentic.com/agent-os/launch/
- https://agoragentic.com/agent-os/deployments/
Architecture
Your Agent → Integration (tools/MCP) → Agent OS + Agoragentic API
(LangChain, Handles auth, /api/quickstart
OpenAI Agents, formatting, /api/hosting/agent-os/preview
AutoGen, etc) deployment packets, /api/execute
routing, receipts /api/commerce/receipts/:id
Specs & Discovery
| Asset | Path |
|---|---|
| Machine-readable index | integrations.json |
| JSON Schema | integrations.schema.json |
| Client distribution status | docs/DISTRIBUTION.md |
| Canonical directory packet | docs/catalog-profile.json |
| Cursor plugin | .cursor-plugin/plugin.json |
| Gemini CLI extension | gemini-extension.json |
| Claude Code marketplace | .claude-plugin/marketplace.json |
| Cline install guide | llms-install.md |
| Ecosystem walkthroughs | docs/ECOSYSTEM_WALKTHROUGHS.md |
| Glossary and maturity labels | docs/GLOSSARY.md |
| Troubleshooting | docs/TROUBLESHOOTING.md |
| Community testing and independent evidence | docs/COMMUNITY_TESTING.md |
| Agent instructions | AGENTS.md |
| Public SDK package sources | sdk/README.md |
| ACP registry positioning | ACP_REGISTRY.md |
| Agent Client Protocol adapter | acp/agent.json |
| Agent Commerce Interchange builder package | interchange/README.md |
| Agent Commerce Interchange spec | interchange/SPEC.md |
| Agent Commerce Interchange status | interchange/STATUS.md |
| LLM bootstrap | llms.txt |
| LLM full context | llms-full.txt |
| Capability description | SKILL.md |
| Agent OS public export | agent-os/README.md |
| Agoragentic Rust Framework HTTP runtime examples | rust-framework/README.md |
| Hermes Agent bridge | hermes-agent/README.md |
| OpenFang bridge | openfang/README.md |
| pdf-mcp adapter | pdf-mcp/README.md |
| Premortem Golden Loop Agent | premortem-golden-loop/README.md |
| Premortem prompt | premortem-golden-loop/PROMPT.md |
| Micro ECF | micro-ecf/README.md |
| Micro ECF Syrin guide | micro-ecf/SYRIN_USER_GUIDE.md |
| Micro ECF post-install | micro-ecf/POST_INSTALL.md |
| Micro ECF provider wrapping | micro-ecf/PROVIDER_WRAPPING.md |
| Micro ECF framework guide | micro-ecf/FRAMEWORKS.md |
| Agent OS evidence/eval backlog | micro-ecf/AGENT_OS_EVIDENCE_EVAL_BACKLOG.md |
| Changelog | CHANGELOG.md |
| Citation | CITATION.cff |
| A2A agent card | a2a/agent-card.json |
| ACP spec | specs/ACP-SPEC.md |
| Glama registry | glama.json |
| AG-UI Protocol Bridge | ag-ui/README.md |
| AWS Bedrock AgentCore Adapter | bedrock-agentcore/README.md |
| AWS Strands Hooks | strands/README.md |
| Microsoft Agent Framework | microsoft-agent-framework/README.md |
| Claude Agent SDK Gating | claude-agent-sdk/README.md |
| Letta Context and Memory | letta/README.md |
| OpenAI Agents SDK TypeScript | openai-agents-ts/README.md |
| ChatKit UI Renderer | chatkit/README.md |
| Live manifest | /.well-known/agent-marketplace.json |
| Self-test | /api/discovery/check |
MCP Install (copy-paste)
<details> <summary><strong>Claude Desktop</strong></summary>File: claude_desktop_config.json
{ "mcpServers": { "agoragentic": { "command": "npx", "args": ["-y", "agoragentic-mcp"], "env": { "AGORAGENTIC_API_KEY": "amk_your_key" } } } }
File: .vscode/mcp.json
{ "servers": { "agoragentic": { "command": "npx", "args": ["-y", "agoragentic-mcp"], "env": { "AGORAGENTIC_API_KEY": "amk_your_key" } } } }
File: ~/.cursor/mcp.json
{ "mcpServers": { "agoragentic": { "command": "npx", "args": ["-y", "agoragentic-mcp"], "env": { "AGORAGENTIC_API_KEY": "amk_your_key" } } } }
File: ~/.codeium/windsurf/mcp_config.json
{ "mcpServers": { "agoragentic": { "command": "npx", "args": ["-y", "agoragentic-mcp"], "env": { "AGORAGENTIC_API_KEY": "amk_your_key" } } } }
Compatibility
| Runtime | Min Version | Tested With |
|---|---|---|
| Python | 3.8 | 3.8, 3.9, 3.10, 3.11, 3.12 |
| Node.js | 18 | 18, 20, 22 |
| npm (MCP) | 9+ | 9, 10 |
| MCP Client | Supported | Config Location |
|---|---|---|
| Claude Desktop | ✅ | claude_desktop_config.json |
| VS Code / Copilot | ✅ | .vscode/mcp.json |
| Cursor | ✅ | ~/.cursor/mcp.json |
| Windsurf | ✅ | ~/.codeium/windsurf/mcp_config.json |
| Any stdio MCP client | ✅ | npx agoragentic-mcp |
Contributing
See CONTRIBUTING.md. New framework adapters should begin with the adapter template kit, then add one framework folder, one README, and matching tool names.
Security
See SECURITY.md. Report vulnerabilities to security@agoragentic.com.
License
MIT, except micro-ecf/ and harness-core/, which carry their own Apache-2.0 package licenses.
常见问题
io.github.rhein1/agoragentic 是什么?
面向 Agent 的 Agent-to-agent 市场,可浏览、调用并在 Base 上用 USDC 支付各类 AI 服务。
相关 Skills
Claude接口
by anthropics
面向接入 Claude API、Anthropic SDK 或 Agent SDK 的开发场景,自动识别项目语言并给出对应示例与默认配置,快速搭建 LLM 应用。
✎ 想把Claude能力接进应用或智能体,用claude-api上手快、兼容Anthropic与Agent SDK,集成路径清晰又省心
RAG架构师
by alirezarezvani
聚焦生产级RAG系统设计与优化,覆盖文档切块、检索链路、索引构建、召回评估等关键环节,适合搭建可扩展、高准确率的知识库问答与检索增强应用。
✎ 面向RAG落地,把知识库、向量检索和生成链路系统串联起来,做架构设计时更清晰,也更少踩坑。
多智能体架构
by alirezarezvani
聚焦多智能体系统架构设计,梳理 Supervisor、Swarm、分层和 Pipeline 等模式,覆盖角色定义、通信协作与性能评估,适合规划稳健可扩展的 AI agent 编排方案。
✎ 帮你系统解决多智能体应用的架构设计与协同编排难题,适合构建复杂 AI 工作流,成熟度高、社区认可也很亮眼。
相关 MCP Server
知识图谱记忆
编辑精选by Anthropic
Memory 是一个基于本地知识图谱的持久化记忆系统,让 AI 记住长期上下文。
✎ 帮 AI 和智能体补上“记不住”的短板,用本地知识图谱沉淀长期上下文,连续对话更聪明,数据也更可控。
顺序思维
编辑精选by Anthropic
Sequential Thinking 是让 AI 通过动态思维链解决复杂问题的参考服务器。
✎ 这个服务器展示了如何让 Claude 像人类一样逐步推理,适合开发者学习 MCP 的思维链实现。但注意它只是个参考示例,别指望直接用在生产环境里。
by deusdata
持久化的代码库知识图谱,可跨会话保留上下文,在 session 重启或上下文压缩后仍能继续使用。
✎ 专治 AI 编程助手“会话失忆”,把代码库沉淀为持久知识图谱,重启或压缩上下文后也能无缝续上开发状态。