agent-shared-memory

Solid

Use when a user asks to inspect coordination memory, propose a durable decision or resolution, review pending memory proposals, or apply an explicitly approved proposal as a new append-only event.

AI & Automation 26 stars 6 forks Updated 6 days ago MIT

Install

View on GitHub

Quality Score: 82/100

Stars 20%
48
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
80
License 10%
100
Description 5%
100

Skill Content

# agent-shared-memory Coordinate durable facts without letting an agent silently rewrite project memory. Read the event schema in references/coord_memory_schema.md before creating or applying a proposal. ## Authority Repository state, current evidence, and recorded human decisions outrank memory. Recall systems are optional caches. All memory mutations start as proposals: .coord/memory-proposals/<proposal-id>.json Without an explicit human approve decision, do not add, supersede, archive, delete, overwrite, or compact canonical memory. ## Modes ### Read Read canonical events and return: - current decisions, following supersedes references - unresolved questions - relevant artifact/evidence pointers - recent execution outcomes - conflicts or stale claims Do not load raw agent logs into the primary session. Follow their stable paths only when needed. ### Propose Create a proposal with: { "schema_version": 1, "proposal_id": "<uuid>", "source_task": "<task id>", "action": { "operation": "add | supersede | archive | delete", "target_ref": null, "summary": "<compact proposed event>", "evidence_refs": ["<stable ref>"] }, "state": "proposed", "created_at": "<ISO 8601>", "decision": null } Supersede, archive, and delete require a specific `action.target_ref`. A proposal with no `action.evidence_refs` remains pending and must not be applied. The `action` object is immutable. Its c...

Details

Author
WenyuChiou
Repository
WenyuChiou/agent-collab-skills
Created
4 months ago
Last Updated
6 days ago
Language
Python
License
MIT

Bundled in these plugins

Similar Skills

Semantically similar based on skill content — not just same category

AI & Automation Listed

aios-memory-propose

Propose and (after explicit review) accept a MemoryOS memory object the correct way — turning a recall/decision into durable accepted memory so future aios_retrieve stops returning null. Bakes in the two mistakes agents repeat: (1) raw .memlang files import 0 blocks — MemLang MUST be a fenced ```memlang block inside a .md file; (2) no silent/bulk auto-accept (DNA invariant 2) — every acceptance is one object with a documented review.

0 Updated 3 weeks ago
cjw0076
AI & Automation Listed

memory-curation

Promote any candidate into the unified memory layer at `.devt/memory/` — ephemeral DEC-xxx into permanent ADR-xxx, retro lesson drafts into LES-xxx, rejected ideas into REJ-xxx tombstones, or reviewing `_suggestions.md` proposals from the discovery engine. Trigger on 'promote this decision', 'capture as ADR/Concept/lesson', 'reject this idea, never suggest again', 'create tombstone', 'review memory suggestions', 'curator review', 'archive stale lesson', 'codify this rule', 'this should be permanent'. Single curation skill for ALL 5 doc types (decision, concept, flow, rejected, lesson). HARD INVARIANT — never writes a permanent `.devt/memory/**/*.md` file without explicit user approval via AskUserQuestion.

0 Updated 5 days ago
emrecdr
AI & Automation Listed

agent-memory

3-tier markdown memory protocol (shared/agent/conversation) for cross-session knowledge. TRIGGER when: reading or writing agent memory files, choosing which memory tier an insight belongs in, or starting a task needing prior context. SKIP: vector recall (use semantic-memory-mcp); distilling conversations into candidates (use distill).

15 Updated 1 months ago
komluk