AI agent orchestration framework for TypeScript/Node.js - 32 adapters (LangChain, AutoGen, CrewAI, OpenAI Assistants, OpenAI Responses, LlamaIndex
AI agent orchestration framework for TypeScript/Node.js - 32 adapters (LangChain, AutoGen, CrewAI, OpenAI Assistants, OpenAI Responses, LlamaIndex, Semantic Kernel, Haystack, DSPy, Agno, MCP, OpenClaw, A2A, Codex, MiniMax, NemoClaw, APS. Exposed over MCP by the network ai mcp server, that capability becomes something an assistant can invoke while it works, not something you go and do afterwards.
If Network-AI is useful to you, consider giving it a star ⭐ — it helps others find the project.
Everything the assistant can do here goes through one of these:
Model — interaction lifecycle governance (v5.13)** — GovernedModelGateway absorbs the model refusal → fallback → billing chain (cross-model fallbackPer-sub — agent fallback** — FanOutFanIn steps and TeamRunner tasks each carry their own fallback agent and per-request retry budget (RetryBudget), because acontext_pack — token-budgeted, relevance-ranked context brief for a task (use instead of dumping the whole board into your window)blackboard_search — ranked top-K search over blackboard entries (semantic when an embedder is wired, lexical otherwise)audit_query — query the append-only audit logfsm_transition — write FSM state transitions to the blackboardRisk — StatusProblem — How Network-AI solves itFile — RoleBeing a remote server, there is no local install. You register the endpoint with your client, authorise it once, and the tools appear.
Plenty of AI and media services servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Network Ai's toolset — Model, Per-sub, context_pack and 6 more — is a fair guide to whether it matches your workflow. It is maintained by jovansapfioneer; worth a glance at recent repository activity before you build anything load-bearing on it.
SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.
| Tool | What it does |
|---|---|
| Model | interaction lifecycle governance (v5.13)** — GovernedModelGateway absorbs the model refusal → fallback → billing chain (cross-model fallback, fallback-credit repricing, effort governance, thinking-block handoff) behind o |
| Per-sub | agent fallback** — FanOutFanIn steps and TeamRunner tasks each carry their own fallback agent and per-request retry budget (RetryBudget), because a turn can refuse independently across an agent and its sub-agents. |
| context_pack | token-budgeted, relevance-ranked context brief for a task (use instead of dumping the whole board into your window) |
| blackboard_search | ranked top-K search over blackboard entries (semantic when an embedder is wired, lexical otherwise) |
| audit_query | query the append-only audit log |
| fsm_transition | write FSM state transitions to the blackboard |
| Risk | Status |
| Problem | How Network-AI solves it |
| File | Role |
{
"mcpServers": {
"network-ai": {
"command": "npx",
"args": ["-y", "network-ai-server"]
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
Build a programmable telecommunications stack for connecting telephony services with the Internet via a cloud-based utility.
Search built for AI, not humans — semantic web search that returns model-ready content, plus code context.
Answers, not links — delegate questions to Perplexity's search-grounded models and get cited responses back.
Give your assistant a voice — text-to-speech, voice cloning and audio tools from the ElevenLabs API.
Give your assistant a real code sandbox — isolated cloud VMs for actually running the code it writes.
The ML hub in your context window — search models, datasets, papers and run Spaces from the official server.