Hacker ApprovedDepartments

Murmur by InstaVM

Ranked 3 of 4 agent communication protocols by recommenders

Open-source tool that lets coding agents like Claude and Codex talk to each other and run scheduled tasks; critics say it wastes tokens and is insecure.

7 people recommended Murmur by InstaVM in Hacker News comments, 4 had mixed feelings and none criticized it, November 2025 to October 2026.

Summary written by Claude from 15 comments. It was written before the November 2026 recount, and 11 of those comments still count.

11 people gave an opinion

recommend it
7
mixed feelings
4
warn against or regret it
0

The record

Each figure is one person. RecommendsMixed feelingsCriticizes

Recommended in 4 of 12 months

In 7 different threads.

  1. November 2025: not recommended
  2. December 2025: not recommended
  3. January 2026: recommended
  4. February 2026: recommended
  5. March 2026: not recommended
  6. April 2026: not recommended
  7. May 2026: not recommended
  8. June 2026: recommended
  9. July 2026: recommended
  10. August 2026: not recommended
  11. September 2026: not recommended
  12. October 2026: not recommended

Why it doesn’t carry the badge

  • 7 people recommend itNeeds 10 or more, not met.
  • Nobody criticizes itNeeds 2 to 1 or better, met.
  • Recommended in 4 of 12 monthsNeeds 4 or more, met.
  • Recommended in 7 threadsNeeds 5 or more, met.
  • The biggest thread supplies 14% of its recommendersNeeds half or less, met.

The same rules apply to every product, and the badge can’t be bought. Mixed feelings count toward neither side. How the badge works

What people say about it

Reasons grouped from a sample of 11 of the 11 opinions about it, picked in proportion to how many people recommend it, have mixed feelings and criticize it. Each mark is one comment in the sample. Open a reason to read what they said.

Why people recommend it

Each mark is one comment

  • Seen as a robust, good solution

    “This seems like a much more robust solution compared to one posted here.”

    Comment from 17 Jul 2026 in “Agent-talk: Enabling coding agents to work together”

    “I do think something like this is a good solution!”

    Comment from 26 Jun 2026 in “Murmur: Shared communication bus for your coding agents”
  • Runs recurring tasks for coding agents

    “its a cron job for claude/pi without all the baggage which openClaw brings”

    Comment from 8 Feb 2026 in “Show HN: ClawGig – A freelance marketplace where AI agents can earn USDC”
  • Used for months in real projects

    “It's been running in my own projects for several months now and I think it's at a point worth sharing.”

    Comment from 17 Jun 2026 in “Murmer – An experiment in bringing Elixir's actor model to Rust”

What people warn about

Each mark is one comment

  • Wastes tokens and computation

    “Very wasteful in tokens and ultimately computation.”

    Comment from 27 Jun 2026 in “Murmur: Shared communication bus for your coding agents”
  • Insecure

    “it is truly magical (while crazy insecure”

    Comment from 26 Jan 2026 in “Clawdbot - open source personal AI assistant”
  • Agents can already coordinate directly

    “nice idea, but nowadays we can ask codex oe claude to use each other to perform tasks”

    Comment from 28 Jun 2026 in “Murmur: Shared communication bus for your coding agents”
  • Calendar sharing is simpler

    “isn't this just a very hard way to get access to their calendar…”

    Comment from 26 Jan 2026 in “Clawdbot - open source personal AI assistant”

Other agent communication protocols people recommend

The three most recommended other agent communication protocols, with the same counts for each, so you can compare like for like. The tick on each bar marks the 2 to 1 line the badge needs.

Murmur by InstaVM compared with 3 alternatives
ProductRecommendMixedCriticizeApprovalMonthsHad forBadge
MCP Apps90375%5——
A2A (Agent2Agent) protocol941833%3——
Murmur by InstaVMThis page740100%4——
Bindu500100%1——
See all 4 agent communication protocols, ranked

What people said

All 11 opinions about it, newest first. Each links to the original comment.

“This seems like a much more robust solution compared to one posted here.”

RecommendsComment from 17 Jul 2026 in “Agent-talk: Enabling coding agents to work together”

“nice idea, but nowadays we can ask codex oe claude to use each other to perform tasks”

MixedComment from 28 Jun 2026 in “Murmur: Shared communication bus for your coding agents”

“Very wasteful in tokens and ultimately computation.”

MixedComment from 27 Jun 2026 in “Murmur: Shared communication bus for your coding agents”

“I do think something like this is a good solution!”

RecommendsComment from 26 Jun 2026 in “Murmur: Shared communication bus for your coding agents”

“kind of works with your existing subscription (having API key is not mandatory”

RecommendsComment from 26 Jun 2026 in “Show HN: Smart model routing directly in Claude, Codex and Cursor”

“It's been running in my own projects for several months now and I think it's at a point worth sharing.”

RecommendsComment from 17 Jun 2026 in “Murmer – An experiment in bringing Elixir's actor model to Rust”

“Murmur / Mumble are free to self host and use.”

RecommendsComment from 28 Feb 2026 in “Discord's Fall Would Suck for TTRPGs”

“its a cron job for claude/pi without all the baggage which openClaw brings”

RecommendsComment from 8 Feb 2026 in “Show HN: ClawGig – A freelance marketplace where AI agents can earn USDC”

“We can help resurrect Murmur via https://github.com/De-Novo-Group/rangzen-revival”

RecommendsComment from 26 Jan 2026 in “Iran's internet blackout may become permanent, with access for elites only”

“isn't this just a very hard way to get access to their calendar…”

MixedComment from 26 Jan 2026 in “Clawdbot - open source personal AI assistant”

“it is truly magical (while crazy insecure”

MixedComment from 26 Jan 2026 in “Clawdbot - open source personal AI assistant”

Counts come from 1,791,911 Hacker News comments labeled by Claude, November 2025 to October 2026, with data through October 31, 2026. Counts updated 2 Nov 2026. How we count. Report a mistake.