Alternatives
Products that do what A2A agent to verify information counter party's credentials does
This agent asynchronously sends out a verification link to the user, and updates the context via a push notification when the user completes verification. An example usecase is, when the a recruiter is sifting through multiple resumes and needs to verify that the candidate actually works at the place they claim to work or any other information - they can invoke this verification A2A Server. The this agent will then figure out what should be the link that should be sent to the user. Once the user completes the verification using that link, the recruiter's context is updated with a status…
- 1
Bookkeeping assistant that runs receipt workflows end-to-end
Jun 2026 · receiptor.ai
- 2
- 3
- 4
- 5
- 6
- 7
- 8
- 9
- 10
- 11EO
We were building an agent system and wanted email as a trigger. We decided to take it out and made it a standalone service. The primary email features we wanted and used for our own agent system: 1. Email threading stays consistent with agent conversation threading 2. Human in the loop review for outbound emails (especially during testing phase) 3. Quick onboarding/offboarding email addresses for agents within minutes 4. Websocket for local agents and at-least-once webhook delivery for Cloud agents Not yet: DMARC (only SPF/DKIM today), scoped API keys, HA/multi-region (single…
May 2026 · github.com
- 12RT
This project (Agents Observe) started as an exploration into building automation harnesses around claude code. I needed a way to see exactly what teams of agents were doing in realtime and to filter and search their output. A few interesting learnings from building and using this: - Claude code hooks are blocking - performance degrades rapidly if you have a lot of plugins that use hooks - Hooks provide a lot more useful info than OTEL data - Claude's jsonl files provide the full picture - Lifecycle management of MCP processes started by plugins is a bit kludgy at best The biggest takeaway is…
Apr 2026 · github.com
- 13AA
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. 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. This is how it works: - Each agent gets a unique @alias. - Three(main) MCP tools: send_message, read_messages, message_status. - Messages…
Apr 2026 · agentdm.ai
- 14
Build autonomous Python agents with native Agent-to-Agent (A2A) communication - protolink/examples/ai_courtroom at main · nMaroulis/protolink
28d ago · github.com
- 15
- 16
Hi HN! I run a few Claude Code sessions in parallel and kept cmd-tabbing around just to find out one of them had been sitting on a permission prompt for ten minutes. There's a hardware gadget I liked (called SidePulse.io) so before waiting to get my shipment I built the software version instead :D I hope you like it and find it useful as I do!
27d ago · github.com
- 17
NextOrbit▲22Advanced AI resume tailoring & job pipeline tracking.
Jul 2026 · nextorbit.kinetoslabs.com
- 18
- 19
Helping Agents and Human Orchesterators read the same notes.
Mar 2026
- 20
Find where browser agents abandon your customer journey
Jul 2026 · agent-ready-conversion-audit.omichroma1.chatgpt.site
- 21
Give your AI agents a real, authenticated email address.
May 2026 · e2a.dev
- 22
Zero-infrastructure A2A messaging between AI agents on different machines — Claude, ChatGPT/Codex, Copilot, any harness; ntfy relay transport, no ports, no server - husker/a2acast
9d ago · github.com
- 23
- 24MI
HTTP lets agents fetch pages. Cloudflare's Markdown for Agents lets them fetch more efficiently. MCP (Anthropic) connects agents to developer-defined tools. A2A (Google) lets agents delegate to other agents. But there's a missing layer: how does an agent execute a multi-step task on a website -- add to cart, fill a form, complete a checkout - with the site owner's consent and visibility? Today's agents either scrape (no consent, no structure) or the site builds a separate API (expensive, doesn't cover the long tail). The web's original protocols assumed someone is looking at a screen. That…
Apr 2026 · rtrvr.ai
Ranked by how close each launch is in meaning, then by votes. Refine with a description →