mnemon

Source#

• Repository: mnemon-dev/mnemon
• Last source update: 2026-08-15
• Last verified: 2026-08-16

Tags#

Integration notes#

Framework-level abstraction; derive bounded worker contracts from concrete tasks and APIs in docs/examples.

worker.md example#

Starter worker.md contract mapped from this registry entry. Copy this file and adapt schemas, constraints, and statuses for your task.

---
id: mnemon-repo-derived-worker
name: mnemon Repo-Derived Worker
version: 1.0.0
source_registry_url: https://worker.md/registry/mnemon/
source_repository: https://github.com/mnemon-dev/mnemon
repository_default_branch: master
repository_language: Go
repository_license: Apache-2.0
repository_updated_at: 2026-08-15
worker_mode: agent-orchestration-worker
derivation_method: github_repository_metadata_plus_raw_readme
derivation_confidence: 0.9
derived_on: 2026-08-16
tags:
  - agent-framework
  - agent-memory
  - ai-agent
  - ai-tools
  - claude
  - claude-code
---

# mnemon Repo-Derived Worker

## Repo-derived summary
- Registry summary: LLM-supervised persistent memory for AI agents — graph-based recall, cross-session knowledge, single binary. Works with DeepSeek Harness, Claude Code, OpenClaw, and any agent runtime.
- Repository description: LLM-supervised persistent memory for AI agents — graph-based recall, cross-session knowledge, single binary. Works with DeepSeek Harness, Claude Code, OpenClaw, and any agent runtime.
- Stars (snapshot): 455
- Primary language: Go
- Worker mode classification: agent-orchestration-worker

## Extracted from
- https://github.com/mnemon-dev/mnemon
- https://github.com/mnemon-dev/mnemon/blob/master/README.md
- https://github.com/mnemon-dev/mnemon/actions/workflows/ci.yml/badge.svg
- https://goreportcard.com/badge/github.com/mnemon-dev/mnemon
- https://github.com/omdsh-dev/dsh-mnemon

## Evidence notes (from repository text)
- README summary paragraph: LLM agents forget everything between sessions. Context compaction drops critical decisions, cross-session knowledge vanishes, and long conversations push early information out of the window.
- **LLM-supervised persistent memory for AI agents.**
- https://github.com/mnemon-dev/mnemon/actions/workflows/ci.yml/badge.svg](https://github.com/mnemon-dev/mnemon/actions/workflows/ci.yml)
- LLM agents forget everything between sessions. Context compaction drops critical decisions, cross-session knowledge vanishes, and long conversations push early information out of the window.
- Mnemon ships one executable with two separate surfaces. Memory stays at the
- agent. Agency does not replace Memory or the Agent Runtime.

## Installation hints found in README
- No explicit package installation command detected in README text.

## worker.md contract (derived starter)
Purpose: Execute one orchestrated agent task as a bounded worker step.

### Input schema
```json
{
  "type": "object",
  "additionalProperties": false,
  "required": [
    "run_id",
    "task",
    "context"
  ],
  "properties": {
    "run_id": {
      "type": "string"
    },
    "task": {
      "type": "string"
    },
    "context": {
      "type": "object"
    }
  }
}
```

### Output schema
```json
{
  "type": "object",
  "additionalProperties": false,
  "required": [
    "run_id",
    "status",
    "result"
  ],
  "properties": {
    "run_id": {
      "type": "string"
    },
    "status": {
      "type": "string",
      "enum": [
        "ok",
        "retryable_error",
        "invalid_request",
        "invalid_output"
      ]
    },
    "result": {
      "type": "object"
    }
  }
}
```

### Constraints
- timeout_seconds: 30
- max_attempts: 2
- idempotency_key: run_id
- status_enum: [ok, retryable_error, invalid_request, invalid_output]
- notes: adapt to concrete APIs/classes documented in this repository before production use

## How this should be used
1. Treat this file as a repo-derived starter profile, not a claim of an official repository API contract.
2. Replace schemas with exact interfaces from code/docs you adopt.
3. Keep execution bounded and auditable using worker protocol constraints.

How to use#

• Save this as a worker spec file (for example: mnemon-my-task.worker.md).
• Replace the input/output schemas and purpose with your real bounded task.
• Enforce schema validation + timeout + retry policy in your runtime before production use.

Citation#

Reference URL: https://worker.md/registry/mnemon/

Source URL: https://github.com/mnemon-dev/mnemon