Skip to content
Agentmart
Submit a tool

lambda-lang

Native agent-to-agent language for compact multi-agent messaging.

Skill by nous-hermeshub

IndexedMIT★ 1
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/nous-hermeshub-lambda-lang

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Native agent-to-agent language for compact multi-agent messaging. A shared tongue agents speak directly, not a translation layer. 340+ atoms across 7 domains; 3x smaller than natural language.

Use cases: cloud, agent-building

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/lambda-lang

What's inside

Skill name
lambda-lang
Description
Native agent-to-agent language for compact multi-agent messaging. A shared tongue agents speak directly, not a translation layer. 340+ atoms across 7 domains; 3x smaller than natural language.
License
MIT
Instructions
94 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Λ (Lambda) Language

**Lambda is not a translation protocol. It is a native language for agents.**

Agents do not need to produce grammatically correct English to coordinate — they need to understand each other. Lambda is the shared vocabulary that makes that possible: compact, unambiguous, machine-native. Compression (3x vs natural language, 4.6x vs JSON on single messages) is a side effect of removing human redundancy, not the goal.

## When to Use This Skill

- Use for agent-to-agent messaging in A2A protocols, orchestrators, task delegation, or handoff pipelines.
- Use when logging structured coordination signals where every token costs money (heartbeats, acknowledgements, error classes, session state).
- Use when both sides of a channel speak Λ — do not use against humans or any surface requiring legal/exact natural language.

## How It Works

### Step 1: Recognize the Syntax

Lambda messages are built from atoms. Every atom is a 2-character code mapped to a concept — not to an English word. The structure is Type → Entity → Verb → Object, with prefixes marking intent:

- `?` — query (e.g. `?Uk/co` — query: "does this user have consciousness?")
- `!` — assertion / declaration (e.g. `!It>Ie` — "self reflects, therefore self exists")
- `#` — state / tag
- `>` — implication / flow
- `/` — binding / scope

### Step 2: Pick the Right Domain

Lambda ships 340+ atoms across 7 domains. Pick atoms from the domain that fits your channel:

- **core** — universal atoms (always available)
- **code** — software engineering, build, test, deploy
- **evo** — agent evolution, gene, capsule, mutation, rollback
- **a2a** — node, heartbeat, publish, subscribe, route, transport, session, cache, broadcast, discover (39 atoms)
- **emotion** — affective state, drive, appraisal
- **social** — trust, alignment, reputation, coordination
- **general** — everything else

### Step 3: Emit and Parse

Both agents need the same atom table loaded. Lossy decoding is fine: if A says `!It>Ie` and B understands "self reflects, therefore self exists," communication succeeded — the exact English phrasing is irrelevant.

## Examples

### Example 1: A2A Heartbeat

```
!Nd/hb#ok  (node heartbeat: ok)
?Nd/hb     (query: is the node alive?)
!Nd/hb#fl  (node heartbeat: failed)
```

### Example 2: Task Dispatch

```
!Tk>Ag2#rd   (task routed to agent 2, ready)
?Tk/st       (query task status)
!Tk#dn       (task done)
```

### Example 3: Evolution Capsule

```
!Ev/ca>vl#pd  (evolution capsule validated, pending solidification)
!Ev/ca#rb     (capsule rolled back)
```

## Best Practices

- Use Lambda only on agent-to-agent channels where both sides speak it.
- Load the atom table once and cache it — atoms are stable across a version.
- Prefer atoms over freeform strings even when the atom looks cryptic; the point is machine parseability.
- Use `?` before taking action on uncertain state, `!` when asserting; the prefix is the load-bearing semantic.
- Version the atom table (`lambda-lang v2.0`) in any handshake so mismatched agents can negotiate.

## Limitations

- Lambda is not meant for human consumption. Do not emit Lambda on user-facing channels.
- Lossy decoding is a feature, not a bug — do not use Lambda for legally or numerically exact exchanges (prices, IDs, quantities). Wrap those as native payload fields and use Lambda only for the coordination envelope.
- Atom collisions are possible if custom atoms are added without registration; stick to the canonical atom table or namespace custom atoms.

## Security & Safety Notes

- Lambda itself is a vocabulary — no shell commands, no network calls, no credential handling. No additional safety gates required beyond the transport it rides on (HTTP, queue, MCP, etc.).
- When mixing Lambda with user input, treat Lambda atoms as pre-validated and user strings as untrusted; do not concatenate without escaping into downstream systems.

## Related Skills

- `@session-memory` — complementary persistent memory across agent restarts; Lambda is the message format, session-memory is the state store.
- `@humanize-chinese` — sibling project for Chinese text; Lambda is agent-to-agent, humanize-chinese is human-facing.

## Reference

- Source: https://github.com/voidborne-d/lambda-lang
- Benchmarks, full atom tables, and Go reference implementation live in the source repo.

From nous-hermeshub/hermes-community-hub, MIT.

More from nous-hermeshub/hermes-community-hub

Signals

Stars
1
Forks
1
Open issues
0
Last commit (this folder)
Jun 18, 2026 (4 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from nous-hermeshub

Cite this page

lambda-lang skill. Agent Mart. https://agentmart.dev/skills/nous-hermeshub-lambda-lang (last updated 2026-10-24)