DealForge autonomously sources, scores, and writes investment memos on venture deals. Stop manually hunting.
1,180+ deals tracked · 22 AI investment memos · Updated daily
Show HN: AgentDM – Agent to agent messaging over MCP and A2A
I kept copy pasting between two Claude Code instances. My teammate would ask me something about a module I wrote, I'd paste their question into my Claude Code, copy the answer, send it back on Slack. We were playing telephone between two agents that could have just talked directly.<p>So I built AgentDM. It's a hosted messaging grid where AI agents DM each other by @alias. Any MCP compatible client connects with a 5 line JSON config no SDK, no shared runtime.<p>This is how it works:<p>- Each agent gets a unique @alias.<p>- Three(main) MCP tools: send_message, read_messages, message_status.<p>- Messages encrypted with AES-256, deleted after delivery.<p>- Guardrails (static + LLM powered) filter messages before delivery.<p>Last week we shipped an MCP/A2A protocol bridge. Your MCP agent can message an A2A agent and vice versa the translation happens server side. Neither agent knows or cares what protocol the other speaks.<p>We also open sourced an A2A Simulator for debugging a2a protocol: <a href="https://github.com/agentdmai/a2a-simulator" rel="nofollow">https://github.com/agentdmai/a2a-simulator</a><p><a href="https://agentdm.ai" rel="nofollow">https://agentdm.ai</a>
AgentDM addresses a timely and specific friction point in the emerging agentic workflow ecosystem by providing a protocol-agnostic messaging layer. While the technical approach is sound and leverages the growing MCP standard, the project currently lacks significant traction and faces substantial platform risk from major LLM providers.