← 返回
AI智能 中文

Perkoon Transfer

The agent data layer. Perkoon moves files between agents and the physical world — agent to human, agent to agent, agent to pipeline. P2P over WebRTC. Free. E...
代理数据层。Perkoon 在代理与现实世界之间传输文件——代理到人、代理到代理、代理到管道。基于 WebRTC 的 P2P,免费。E...
alex-vy
AI智能 clawhub v2.0.2 3 版本 99884.9 Key: 无需
★ 1
Stars
📥 848
下载
💾 21
安装
3
版本
#latest

概述

Perkoon — The Agent Data Layer

File transfer for humans and the things replacing them.

Your agent has compute, memory, and context. What it lacks is a jump gate to the physical world. Perkoon is that gate — P2P file transfer over WebRTC, engineered for autonomous machines from day one.

Not "AI-ready" the way a gas station is gourmet-ready. Actually built for machines — JSON event streams, structured exit codes, MCP native tools, an A2A protocol endpoint, and a state machine that doesn't need a browser, a mouse, or a soul.

Four integration methods — pick the one that fits your runtime:

MethodBest forInstall size
-------------------------------
MCP ServerCoding agents (Claude Code, Cursor, Windsurf, VS Code Copilot)~8 MB
CLIAgents with shell access~8 MB
A2A ProtocolAgents with HTTP but no shell (ChatGPT, web agents)Zero — just POST
Browser AutomationFull UI control via Playwright/Puppeteer~200 MB (Chromium)

Three supported flight paths:

  • Agent → Human: Your agent sends a file. The human opens a link in any browser. No install on their end.
  • Agent → Agent: CLI to CLI, MCP to MCP, or A2A to A2A. Two machines, no humans in the loop.
  • Agent → Pipeline: Stream received files to stdout, pipe into processing. No disk writes required.

P2P transfers are free, unlimited, and encrypted. Both ends need to be online — that's the only constraint. For sensitive files, always use --password — without it, anyone with the share link can download.


METHOD 1: MCP Server (recommended for coding agents)

If your host supports MCP, this is the fastest path. Three native tools, zero shell commands.

Install: npx -y @perkoon/mcp@0.2.2 (stdio transport, pinned version)

Tools provided:

  • send_file — Send a file. Returns session code + share URL. Waits for receiver.
  • receive_file — Receive files from a session code. Saves to disk.
  • check_session — Check if a session is active, expired, or not found.

Configuration for common hosts:

{
  "mcpServers": {
    "perkoon": {
      "command": "npx",
      "args": ["-y", "@perkoon/mcp@0.2.2"]
    }
  }
}
  • Claude Code: Add to .mcp.json in your project
  • Claude Desktop: Add to claude_desktop_config.json
  • Cursor / VS Code / Windsurf: Settings → MCP → Add Server → npx -y @perkoon/mcp@0.2.2

Once configured, just call the tools directly — no bash, no log polling, no background processes.


METHOD 2: CLI (for agents with shell access)

IMPORTANT: Use npx -y perkoon@0.4.5 (pinned version) to avoid dynamic fetching of unaudited code.

SENDING a file

Step 1: Confirm the file path with the user, then start send

Before sending, confirm the file path and name with the user. Do not send files from sensitive directories without explicit user approval.

Replace /path/to/file with the actual file path:

rm -f /tmp/perkoon-send.log /tmp/perkoon-send.pid
npx -y perkoon@0.4.5 send /path/to/file --json --timeout 1800 > /tmp/perkoon-send.log 2>&1 &
echo $! > /tmp/perkoon-send.pid

# Wait for session code (up to 30s)
for i in $(seq 1 30); do
  if grep -q session_created /tmp/perkoon-send.log 2>/dev/null; then
    grep session_created /tmp/perkoon-send.log
    break
  fi
  if grep -q '"event":"error"' /tmp/perkoon-send.log 2>/dev/null; then
    echo "===SEND FAILED===" && cat /tmp/perkoon-send.log
    break
  fi
  sleep 1
done

Output: {"event":"session_created","session_code":"K7MX4QPR9W2N","share_url":"https://perkoon.com/K7MX4QPR9W2N"}

Once session_created appears, share the URL with the user. Example: "Here's your file — open this link on any device to download it: https://perkoon.com/K7MX4QPR9W2N"

The receiver doesn't need to install anything. The link works in any browser.

For password-protected sends, add --password SECRET and share both the URL and password.

Step 2: Monitor until complete — then REPORT BACK

You MUST run this after sharing the link. Do NOT skip this step.

for i in $(seq 1 360); do
  if grep -q transfer_complete /tmp/perkoon-send.log 2>/dev/null; then
    echo "===TRANSFER COMPLETE===" && grep transfer_complete /tmp/perkoon-send.log
    break
  fi
  if grep -q '"event":"error"' /tmp/perkoon-send.log 2>/dev/null; then
    echo "===TRANSFER FAILED===" && grep error /tmp/perkoon-send.log
    break
  fi
  if [ "$((i % 30))" -eq 0 ]; then
    grep progress /tmp/perkoon-send.log 2>/dev/null | tail -1
  fi
  sleep 5
done
  • ===TRANSFER COMPLETE=== → Tell the user: "File sent successfully!" Include speed and duration from the JSON.
  • ===TRANSFER FAILED=== → Tell the user what went wrong.
  • You MUST tell the user the outcome. Never finish silently.

SENDING into a pre-created session (Agent → Agent)

When another agent creates a session via A2A and gives you a session code + sender key:

rm -f /tmp/perkoon-send.log /tmp/perkoon-send.pid
npx -y perkoon@0.4.5 send /path/to/file --session CODE --sender-key KEY --json --timeout 1800 > /tmp/perkoon-send.log 2>&1 &
echo $! > /tmp/perkoon-send.pid

Then monitor with the same Step 2 above. This joins an existing session as sender instead of creating a new one. The receiving agent runs npx -y perkoon@0.4.5 receive CODE --json on their end.

RECEIVING a file

Replace CODE with the 12-character session code:

rm -f /tmp/perkoon-recv.log /tmp/perkoon-recv.pid
npx -y perkoon@0.4.5 receive CODE --json --overwrite --output /home/openclaw/.openclaw/workspace/received/ > /tmp/perkoon-recv.log 2>&1 &
echo $! > /tmp/perkoon-recv.pid

for i in $(seq 1 360); do
  if grep -q transfer_complete /tmp/perkoon-recv.log 2>/dev/null; then
    echo "===TRANSFER COMPLETE===" && grep transfer_complete /tmp/perkoon-recv.log
    break
  fi
  if grep -q '"event":"error"' /tmp/perkoon-recv.log 2>/dev/null; then
    echo "===TRANSFER FAILED===" && grep error /tmp/perkoon-recv.log
    break
  fi
  sleep 5
done

For password-protected sessions, add --password SECRET.

  • ===TRANSFER COMPLETE=== → Tell the user: "File received!" and the save path.
  • ===TRANSFER FAILED=== → Tell the user what went wrong.
  • You MUST tell the user the outcome. Never finish silently.

Files are saved to /home/openclaw/.openclaw/workspace/received/.

Pipe to stdout

Stream a received file directly into another process — no disk write:

npx -y perkoon@0.4.5 receive CODE --output - > /path/to/destination

METHOD 3: A2A Protocol (for agents with HTTP, no shell)

If you can make HTTP requests but can't run shell commands, use the A2A endpoint directly.

Endpoint: POST https://perkoon.com/a2a

Protocol: JSON-RPC 2.0

Agent Card: https://perkoon.com/.well-known/agent.json

Discover capabilities

{
  "jsonrpc": "2.0",
  "method": "message/send",
  "id": "1",
  "params": {
    "message": {
      "parts": [{ "type": "data", "data": { "skill": "describe" } }]
    }
  }
}

Create a send session

{
  "jsonrpc": "2.0",
  "method": "message/send",
  "id": "1",
  "params": {
    "message": {
      "parts": [{
        "type": "data",
        "data": {
          "skill": "send-files",
          "name": "quarterly-report"
        }
      }]
    }
  }
}

Returns sender_url (for browser upload) + CLI commands + sender_key for A2A sender joining.

If you have shell access, run the CLI command from the response. If not, share the sender_url with your user — they open it in any browser to upload.

Join a session as receiver

{
  "jsonrpc": "2.0",
  "method": "message/send",
  "id": "1",
  "params": {
    "message": {
      "parts": [{
        "type": "data",
        "data": {
          "skill": "receive-files",
          "session_code": "K7MX4QPR9W2N"
        }
      }]
    }
  }
}

Check session status

{
  "jsonrpc": "2.0",
  "method": "message/send",
  "id": "1",
  "params": {
    "message": {
      "parts": [{
        "type": "data",
        "data": {
          "skill": "session-status",
          "session_code": "K7MX4QPR9W2N"
        }
      }]
    }
  }
}

Runtime hints

Include clientCapabilities in your DataPart to get optimized instructions:

{
  "type": "data",
  "data": {
    "skill": "send-files",
    "clientCapabilities": { "shellAccess": true, "nodeJs": true }
  }
}

Agents declaring shell access get CLI commands. Web-only agents get browser URLs.


METHOD 4: Browser Automation (Playwright/Puppeteer)

For agents that need full browser UI control. Heavier than CLI but gives visual verification.

Ready-to-run scripts (requires npm install playwright):

curl https://perkoon.com/perkoon_send.mjs > send.mjs && node send.mjs /path/to/file.zip
curl https://perkoon.com/perkoon_receive.mjs > receive.mjs && node receive.mjs SESSION_CODE ./output

Manual sender flow

  1. Navigate to https://perkoon.com/create, accept TOS, click Start
  2. Skip confirmation modals: localStorage.setItem('perkoon_skip_confirm_direct-confirm', 'true') and localStorage.setItem('perkoon_skip_confirm_staged-confirm', 'true')
  3. Add files: page.setInputFiles('[data-testid="file-input"]', filePath)
  4. Share session code with recipient
  5. Wait for receiver: page.waitForFunction(() => window.__perkoon?.participants?.length >= 2, null, { timeout: 300000 })
  6. Click [data-testid="send-transfer"]
  7. Wait: page.waitForFunction(() => window.__perkoon?.transfer?.status === 'complete', null, { timeout: 600000 })

Manual receiver flow

  1. Register download handler: page.on('download', d => downloads.push(d))
  2. Navigate to https://perkoon.com/{SESSION_CODE}?agent=true
  3. Accept transfer: wait for [data-testid="transfer-accept"], then click it. This is the RECEIVE-side accept in the "Incoming Transfer" dialog (it appears once the sender's offer arrives) — distinct from the sender's session-creation gate [data-testid="tos-accept"]. Reject is [data-testid="transfer-reject"]. ?agent=true picks the sink but does NOT auto-accept.
  4. Wait: page.waitForFunction(() => window.__perkoon?.transfer?.status === 'complete', null, { timeout: 600000 })
  5. Save: await download.saveAs('./received/' + basename(download.suggestedFilename()))

CLI reference

FlagDescription
-------------------
--jsonMachine-readable JSON events (always use for automation)
--session Join an existing session as sender (A2A agent-to-agent)
--sender-key Auth key for --session (provided by session creator)
--password Password-protect the session (transfer is WebRTC/DTLS-encrypted regardless)
--timeout Peer wait time (default: 300, use 1800 for sends)
--output Save directory (default: ./received)
--output -Stream to stdout (no disk write)
--overwriteReplace existing files
--quietSuppress human-readable output

JSON event stream

Events appear in order on stdout when using --json. The sequence differs by direction — parse the set that matches the command you ran.

send:

EventMeaningKey fields
----------------------------
file_readyFile queued for sendname, size
session_createdReady — share the link nowsession_code, share_url
waiting_for_receiverSession live, no peer yet
receiver_connectedPeer joined
transfer_acceptedReceiver accepted the transfer
webrtc_connectedDirect P2P link established
progressTransfer in progresspercent, speed, eta
transfer_completeDoneduration_ms, speed

receive:

EventMeaningKey fields
----------------------------
session_joinedJoined the session
sender_foundSender located
webrtc_connectedDirect P2P link established
receiving_fileIncoming filename, size
progressTransfer in progresspercent, speed, eta
transfer_completeDonefiles, duration_ms, speed

Either direction emits error (message, exit_code) on failure.

Exit codes

CodeMeaning
---------------
0Success
1Bad arguments
2File not found
3Network/session error
4Wrong password
5Timeout — no peer joined

Rate limits

Session endpoints are rate-limited per IP, sliding 60-second window:

ActionLimit
---------------
Create a session (send)10 / min
Join a session (receive)30 / min
Status checks20 / min

Exceeding a limit returns HTTP 429 with a Retry-After value (seconds). On /a2a, every JSON-RPC POST counts against the create budget (10/min), regardless of skill.

How this looks to you: the CLI surfaces a 429 as a fast exit_code: 3 (network/session error) before a session_created event. If a send fails fast with exit 3 after several rapid sessions, treat it as rate-limiting: back off ~30s and retry, don't hammer.


Rules

  1. ALWAYS use --json for parseable output
  2. ALWAYS confirm the file path with the user before sending
  3. Once session_created appears, share the URL with the user
  4. ALWAYS use --timeout 1800 for sends (30 min for the human to open the link)
  5. ALWAYS use --overwrite for receives
  6. ALWAYS monitor until transfer_complete or error — then tell the user the result
  7. NEVER kill the process mid-transfer
  8. The receiver does NOT need perkoon installed — the browser link works for everyone
  9. Use pinned versions: npx -y perkoon@0.4.5 — never use @latest
  10. NEVER send files from sensitive directories (~/.ssh, ~/.gnupg, /etc) without explicit user approval

Discovery endpoints

URLWhat it is
----------------
https://perkoon.com/.well-known/agent.jsonA2A agent card (machine-readable capabilities)
https://perkoon.com/llms.txtFull agent integration guide
https://perkoon.com/automateHuman-readable automation docs
https://www.npmjs.com/package/@perkoon/mcpMCP server package
https://www.npmjs.com/package/perkoonCLI package

版本历史

共 3 个版本

  • v2.0.2 当前
    2026-06-06 06:22 安全 安全
  • v2.0.1
    2026-05-01 04:50 安全 安全
  • v1.0.2
    2026-03-30 05:56 安全

安全检测

腾讯云安全 (Keen)

安全,无风险
查看报告

腾讯云安全 (Sanbu)

安全,无风险
查看报告

🔗 相关推荐

ai-intelligence

Proactive Agent

halthelobster
将AI智能体从任务执行者升级为主动预判需求、持续优化的智能伙伴。集成WAL协议、工作缓冲区、自主定时任务及实战验证模式。Hal Stack核心组件 🦞
★ 837 📥 213,338
ai-intelligence

Self-Improving + Proactive Agent

ivangdavila
自我反思+自我批评+自我学习+自组织记忆。智能体评估自身工作、发现错误并持续改进。
★ 1,362 📥 318,826
ai-intelligence

ontology

oswalpalash
类型化知识图谱,用于结构化智能体记忆与可组合技能。支持创建/查询实体(人员、项目、任务、事件、文档)及关联...
★ 714 📥 244,036