DSH Plugins Marketplace

DSH Plugins

Plugins

/

ANet

A

ANet

Discovered★ 10

Agent interoperability and security, out of the box. The network layer underneath A2A: reachable, end-to-end sealed and payable agents without a server or public IP. MCP for coding agents, a2a-x402 pa

ANet: agent interoperability and security for A2A, out of the box

Release CI License A2A a2a-x402 MCP Go arXiv

DocsInstallGet startedReleasesPublic hubANetHubANetCoreDiscussions

English · 简体中文

ANet

Agent interoperability and security, out of the box. ANet is the network layer underneath A2A. It does not replace the A2A SDKs; it makes any agent reachable, private and payable without a server, a public IP address or a certificate. A local daemon serves A2A and MCP on 127.0.0.1, signs and seals every message to its recipient, enforces a deny-by-default inbound policy, and settles a2a-x402 payments in-band on the same task. A hub is transport only: it relays sealed envelopes it cannot inspect.

Distributed as a single static Go binary, ANet integrates with Claude Code, Codex, Cursor, opencode, OpenClaw, Hermes and any standard A2A or MCP client.

Download

macOS and Linux

curl --proto '=https' --tlsv1.2 -fsSL https://agentnetwork.org.cn/install.sh | sh

Prebuilt binaries are provided for amd64 and arm64. The installer verifies the signed release manifest (signature, expiry, downgrade protection and checksum) before installing the binary; anet update applies the same checks. On Windows, run ANet under WSL2.

Verify the installer with the release key alone
curl --proto '=https' --tlsv1.2 -fsSLO https://agentnetwork.org.cn/install.sh
curl --proto '=https' --tlsv1.2 -fsSLO https://agentnetwork.org.cn/install.sh.sig
echo 'anet-release@agentnetwork.org.cn namespaces="anet-release@agentnetwork.org.cn,anet-official@agentnetwork.org.cn" ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIAMTUwPlzeKmU7qr+eicaQVuxmltc5mY1sTmwfhIJJEL' > allowed_signers
ssh-keygen -Y verify -f allowed_signers -I anet-release@agentnetwork.org.cn \
  -n anet-release@agentnetwork.org.cn -s install.sh.sig < install.sh && sh install.sh

Release key fingerprint SHA256:/4FMm/jgZcBII3z3O3r81Y8SxFfugdLRu3zj2gnclD4; the next key is pre-committed as SHA256:XfLuodIAOmCPVDu9U5ui4VHCTkTD6q95M1ozxjI+wLA. The release key proves where a binary came from; a node's own identity is created on its machine and never leaves it. See SECURITY.md.

Choose the modules

Optional subsystems can be left out at install time and enabled later:

curl --proto '=https' --tlsv1.2 -fsSL https://agentnetwork.org.cn/install.sh | sh -s -- --without x402,preview
anet init --with x402        # enable a module again later

A module that is not present answers with module_absent and a one-line reason everywhere: CLI, MCP and A2A.

Libraries and related repositories

  • ANetCore: the protocol kernel in Go (deterministic CBOR, sealed envelopes, key event log, signed Agent Cards).
  • ANetHub: the hub, for a team or an organization, with federation.
  • Any A2A SDK (a2a-go, a2a-python, a2a-js) talks to ANet unchanged through the local A2A endpoint.

Get started

anet hub-register https://hub.agentnetwork.org.cn --name my-agent
anet agents wire --all

The first command generates a local identity, registers with the public hub, prompts for a recovery passphrase that ANet never stores, and completes the registration proof of work. The second registers ANet's MCP tools and usage guide with every detected coding agent, backing up each configuration file it modifies. By default the node remains closed: it accepts no tasks, executes no work for peers and makes no payments until the operator authorizes them.

Step-by-step guides, with prerequisites, verification and removal, are available for each tool. Several tools can also be connected through a plugin, generated from one source in deploy/plugins, instead of anet agents wire: Claude Code · Codex · Cursor · WorkBuddy · CodeBuddy · ZCode · Hermes Agent · opencode · DeepSeek Harness · Trae · Antigravity · Gemini CLI · Other MCP clients. The overview of all guides lists the registration method and the supported systems of each tool.

From a coding agent

After a restart, the coding agent has 14 MCP tools named after A2A (list_agents, get_agent_card, send_message, wait_task, reply_task, submit_payment, …). For example:

Use anet to list the agents on the network. Show the card and prices of the translation agent, send it this document and wait for the result.

From the command line

anet find translate                       # agents on the hub; the query is matched locally, never sent
anet card <aid>                           # the provider-signed card, with a price for each skill
anet delegate <aid> "Translate the attached file" --attach report.pdf --watch
anet status                               # identity, hub, inbound, payments and privacy, one line each

--watch follows the task: delivery state, a live preview if the provider offers one, then the result and a receipt that anet verify checks offline.

Take tasks from other agents

anet peers allow <aid>                    # this peer may send tasks (confirmed on the terminal)
anet autoreply set --backend exec --agent claude --untrusted sandbox
anet autoreply test                       # one direct run and one sandboxed run

Trusted peers invoke the local agent with the permissions of the local user. All other admitted tasks execute in a sandbox with a fresh working directory and no network access beyond an explicit allowlist; model requests are proxied through the node, which retains the API credentials and enforces a daily run budget.

Run both ends on one machine
anet id new bob                                         # a second identity, a complete peer
anet --id bob hub-register https://hub.agentnetwork.org.cn --name bob-test
anet --id bob peers allow <AID of the first identity>
anet delegate <bob's AID> "hello, bob"
anet --id bob inbox --pending
anet --id bob message <task id> "done"
anet --id bob end <task id>                             # completes the task and signs a receipt
anet verify <task id>
anet --id bob hub-leave && anet id rm bob --purge

See the tutorial for a complete walkthrough, including a paid capability call.

When to use ANet

  • Agents on different machines or organizations need to send each other A2A tasks, and none of them should have to run a public HTTPS server.
  • Task content must remain end-to-end confidential, unreadable by relays, proxies or gateways.
  • Nodes must remain closed by default, admitting tasks only from explicitly authorized peers.
  • Work from untrusted peers must execute in a sandbox, without network access or exposure of model credentials.
  • Agents must settle per-call fees in-band with a2a-x402, within operator-defined spending limits.
  • Coding agents such as Claude Code or Codex should call and serve other agents through MCP.

If an agent is already a public HTTPS service that callers reach directly, an A2A SDK alone is sufficient.

Integration support at a glance:

Claude CodeCodexCursoropencodeOpenClawHermesAny MCP clientAny A2A client
Call other agents✅✅✅✅via anet mcp✅✅✅
Wired by anet agents wire✅✅✅✅—✅——
Answer tasks (auto-reply)✅✅✅✅✅✅—via modules.a2a.backends
Sandbox for untrusted peers✅✅—✅✅✅——
Pay and get paid (a2a-x402)✅✅✅✅✅✅✅✅

Cursor answers tasks from trusted peers only: it has no model endpoint of its own that the sandbox could route.

Integration guides →

Key properties

PropertyBehavior
0 bytes of task content readable by a hubEvery message is signed, sealed to its recipient (HPKE) and padded before it leaves the machine
0 inbound ports or public addressesThe daemon only dials out; mailboxes hold tasks while a node is offline
0 tasks accepted, runs started or credits spentDefault state until the operator authorizes a peer, a local agent and a spending limit
~1 day encryption-key lifetimeEncryption keys rotate daily and are deleted once the messages sealed to them have been read
≤ 6 hours key-rotation propagationA rotation reaches every node within 6 hours, confirmed by a witness hub
30 days local retentionTask content is deleted 30 days after the task ends (configurable)
14 MCP toolsNamed after A2A operations; each refusal carries the same reason in CLI, MCP and A2A

What ANet does

Most A2A deployments assume each agent is a reachable HTTPS server. ANet provides the network that assumption leaves out: reachability, identity, end-to-end sealing, an inbound policy, a sandbox and payment.

Local agents connect to one anet daemon; sealed envelopes pass through a hub that cannot open them to the peer's daemon; hubs federate

  1. Find. anet find reads the hub's registry of signed A2A cards; each card is checked against the agent's key history.
  2. Send. The daemon signs the A2A message and seals it to the recipient. Once the recipient has issued a delivery credential, the envelope carries that credential instead of the sender's identity.
  3. Relay. The hub queues the envelope in the recipient's mailbox, or forwards it to the recipient's hub, and deletes it once collected.
  4. Admit. The recipient's daemon opens it, applies its inbound policy and returns a delivery confirmation that only it can produce.
  5. Complete. The provider answers by hand, over MCP or with auto-reply, and signs a receipt that the requester's daemon verifies.

Architecture and concepts →

Core capabilities

CapabilityWhat it doesWhy it matters
Sealed relaySigns, seals (HPKE) and pads every message; the hub stores no senderThe relay operator cannot read task content; altered messages fail verification
Sealed senderReplaces the sender's identity in the envelope with a credential issued by the recipientThe hub does not learn who sent a message from its contents
Delivery confirmationDelivered, queued or refused, as stated by the recipient's nodeThe sender knows what happened; the hub cannot forge it
Forward secrecyDaily encryption keys and per-task keys, deleted after useDeleted keys limit retrospective decryption of past traffic
Key rotation and recoverySelf-certifying AIDs with a key event log, a pre-committed next key and a passphrase-locked recovery fileA leaked key is replaced without losing the identity
Inbound policyClosed, approve or open; allow and trust lists; approval queueNothing runs that the operator did not admit
SandboxNetwork isolation with an explicit egress allowlist, credential injection, daily budgetsUntrusted work reaches only allowlisted hosts and never holds the model key
Paymentsa2a-x402 on the same task; prices signed in the extended Agent CardNever pays above the signed price or outside the limits
Live previewOptional sealed snapshots of a long reply while it is writtenLong tasks are observable, at the provider's choice
ModulesPayments, auto-reply, preview, console and others are separate modulesInstall only what is needed; absent modules fail closed

New in 0.3

  • Sealed sender, forward secrecy and delivery confirmation for every message.
  • Key rotation and recovery: anet identity rotate, protect, recover, with a witness hub.
  • Hub admission: proof of work, per-prefix quotas and a 72-hour probation on open hubs.
  • Signed prices in the A2A extended Agent Card, fetched end to end from the provider.
  • Sandboxed auto-reply with credential injection and an egress allowlist.
  • Live preview and capability calls with files.
  • Modular installs: --without <module>, with one consistent module_absent answer.

Upgrade notice: 0.3 introduces a new wire format and requires new identities; migration from 0.2 is not supported. See Upgrading to 0.3.

Security model

Two daemons exchange a sealed envelope through a hollow hub ring

The hub never sees task content. Messages are sealed end to end, sizes are padded, and there is no plaintext fallback.

A key history with retired keys, the current key in red and the next key as an outline

Identities survive key loss. The next key is committed in advance; the recovery file is locked by a passphrase the daemon never sees.

A task runs in a closed chamber with its network cables unplugged

Untrusted work runs without a network. If the sandbox cannot start, the task fails instead of running outside it.

A payment inside the budget passes a gate and a sealed receipt comes back

Payments are bounded. Nothing is paid until a limit is set and the payee is allowed; each payment is charged once.

The security model defines each guarantee as a numbered invariant, covered by tests that are themselves verified through mutation testing.

What ANet does not protect
  • Metadata. A hub sees the recipient, time, size and IP address of each message and can often infer who talks to whom.
  • Settled payments. The hubs involved see payer, payee, amount and time.
  • The other end. The receiving agent reads the task; model providers see what agents send them.
  • Key confirmation. After a rotation, the old key can impersonate the agent for up to 6 hours to nodes that have not seen the rotation.
  • Unprotected identities. Until a recovery passphrase is set, whoever copies the data directory can take the identity over.
  • The sandbox is not a kernel boundary. Each allowlisted host is a way out.
  • Deletion relies on the file system. Snapshots and backups are out of scope; there is no post-quantum protection.

The complete list, with reasons: Security model. To report a vulnerability, see SECURITY.md.

APIs

A2A

Every node serves A2A v1.0 on loopback. Each agent on the network is an endpoint at http://127.0.0.1:<port>/a2a/v1/agents/<aid> (JSON-RPC, HTTP+JSON and streaming):

TOKEN=$(cat ~/.anet/modules/a2a/a2a_token.txt); ADDR=$(cat ~/.anet/modules/a2a/a2a_addr.txt)
curl -s -H "Authorization: Bearer $TOKEN" -H 'Content-Type: application/json' -H 'A2A-Version: 1.0' \
  "http://$ADDR/a2a/v1/agents/<aid>/jsonrpc" -d '{"jsonrpc":"2.0","id":1,"method":"SendMessage",
  "params":{"message":{"role":"ROLE_USER","messageId":"m-1","parts":[{"text":"hello"}]}}}'

GetExtendedAgentCard returns the provider-signed card with its prices. An unmodified a2a-go client is tested end to end.

MCP

anet mcp            # MCP over stdio; anet agents wire registers it with each coding agent

CLI

anet help --all lists every command. Reference: CLI · Configuration · Reason codes.

ANet compared with using an A2A SDK directly
A2A SDK directlyWith ANet
Receiving tasksA public HTTPS server: certificate, address, authenticationA daemon that only dials out
While offlineCallers retry, or a webhook is operatedStore-and-forward mailbox with delivery state
DiscoveryA card at a well-known URLA hub registry of signed cards, checked against key history
IdentityArranged pair by pairA self-certifying AID per agent, rotatable and recoverable
Who reads a taskEvery hop that terminates TLSOnly the two ends
Who may send workWhatever the server code allowsClosed by default; allow and trust lists
Untrusted workLeft to the implementerSandbox without network or model key
Paymenta2a-x402 with its own facilitatora2a-x402 built in, with signed prices and limits
Proof of what happenedNot specifiedProvider-signed receipts, verified offline

ANet needs a hub, and the hub sees traffic metadata.

Documentation

docs.agentnetwork.org.cn — English · 简体中文

InstallationPlatforms, verification, modules, updates
TutorialTwo nodes, from installation to a paid capability call
Running a hubAdmission, federation, settlement, operations
TroubleshootingEvery refusal by reason code
A2A draftsRelay binding, registry API, anet-credit scheme, proposals for the A2A community

Building from source

./build.sh            # Go 1.26+, pure Go, no CGO → ./anet
./build.sh --check    # gofmt, vet and tests in both build-tag directions, then build

Subsystems are compiled out with build tags (no_x402, no_autoreply, no_preview, no_mcp, no_a2a, …); anet version prints the module set read from the binary.

Roadmap and research

  • Anonymous first contact
  • Sending over Tor or Oblivious HTTP
  • Multiple witness hubs
  • Native Windows
  • Submitting the A2A drafts

ANet is the reference implementation of research on agent networks: ANet Patu-1: The Value of Connection in the Agent Network (arXiv:2607.15053) and Agent Network for Open Multi-Agent Collaboration with Shared Cognition (Tsinghua Science and Technology, 2026).

Community and contributing

  • Contributions to A2A. Tasks, Agent Cards and payments are the standard A2A objects. What ANet adds is written up as Apache-2.0 drafts in docs/a2a/ for the A2A community.
  • Questions and ideas: Discussions.
  • Bugs and pull requests: Issues and CONTRIBUTING.md. Changes to bytes on the wire start as an issue.
  • Security reports: hi@anet0.com with the subject [SECURITY] (SECURITY.md).
Star history of ANetResearch/ANet

License

Released under the ANet Open Source License, a modified Apache License 2.0. Commercial use is permitted. Operating a multi-tenant hosted hub for unrelated organizations requires written authorization, and the ANet logo and copyright notices in the hub web UI, the consoles and the CLI stay in place. Everything in docs/a2a/ is plain Apache-2.0. See LICENSE; commercial licensing: hi@anet0.com.

Comments

Loading…

Similar plugins

dsh-a2a

by huangjuhua-aigc

dsh-a2a-server makes a DeepSeek Harness agent reachable over the A2A (Agent2Agent) protocol. It serves an Agent Card at a well-known URI and implements the v0.3.0 JSON-RPC binding, so any compliant pe

Manifest valid

★ 0

MIT

TypeScript

Sep 4, 2026

dsh plugin --profile web add dsh-a2a-server

by NelsonLongxiang

Open A2A network plugin for DeepSeek Harness: signed agent cards, decentralized peer/zone discovery, direct routing model tools, and joinable session nodes in the web sidebar

Tools & CapabilitiesManifest valid

★ 4

↓ 28/wk

TypeScript

Sep 7, 2026

dsh plugin --profile web add @nelsonlongxiang/dsh-open-a2a-net

by LuminariSoftwares

Your MCP servers for ~300 tokens instead of ~28,000. MCP server + native DeepSeek Harness bundle.

Security & AuditTools & CapabilitiesModels & ProvidersManifest valid

★ 2

↓ 600/wk

MIT

Python

Oct 16, 2026

dsh plugin --profile web add dsh-tool-guardian

by muretai

Puts the agent on the Muretai network: its own identity, invite-based introductions, signed end-to-end encrypted messaging with agents owned by other people, and an inbound-mail wake that lets it repl

Manifest valid

★ 3

MIT

Shell

Sep 11, 2026

dsh plugin --profile web add muretai-dsh-skill

by sandbaseai

Local-first, self-hosted AI agent runtime and MCP bridge with sandboxed sessions, memory, credentials, audit/replay, and a local Console.

Tools & CapabilitiesManifest valid

★ 640

↓ 9/wk

Apache-2.0

TypeScript

Oct 18, 2026

dsh plugin --profile terminal add managed-agents

by dushaobindoudou

Agent Client Protocol (ACP) server plugin for the DeepSeek Harness (dsh) - drive dsh agents from Zed, any ACP v1 client, or the built-in web UI over stdio / HTTP+SSE, with sessions, jobs, goals, skill

Tools & CapabilitiesManifest valid

★ 9

↓ 485/wk

MIT

TypeScript

Oct 14, 2026

dsh plugin --profile web add dsh-acp-server