agent-memory
/agent-memory
Obsługuje lokalną pamięć plikową repozytorium w .scaffolding/ (warstwy wspólna, agenta i rozmowy) i pomaga zdecydować, do której warstwy trafia dana informacja.
- Autor
- komluk ↗
- Repozytorium
- scaffolding ↗
- Licencja
- MIT
- Ostatnia zmiana repozytorium
- 27.10.2026
Ocena i bezpieczeństwo
- Pliki w paczce
- 1
- Skrypty
- 0
- Komentarze HTML
- 3
- Adresy URL w SKILL.md
- 0
Brak sygnałów. Repozytorium zmienione 27.10.2026, bez odwołań do wycofanych modeli i API.
MIT, otwarta: można używać i zmieniać, z zachowaniem informacji o autorze.
- SKILL.md zawiera komentarze HTML (3). Nie widać ich w podglądzie Markdown, a model je czyta.
Co robi i kiedy
Obsługuje lokalną pamięć plikową repozytorium w .scaffolding/ (warstwy wspólna, agenta i rozmowy) i pomaga zdecydować, do której warstwy trafia dana informacja.
Oryginalny opis (EN)
Repo-local file memory under .scaffolding/ (shared/agent/conversation tiers). TRIGGER when: reading or writing .scaffolding/ memory files, or choosing which file tier an insight belongs in. SKIP: vector memory / MCP search and store (use semantic-memory-mcp); distilling conversations (use distill).
Jak działa
- Memory Tiers
- How Memory Is Read
- On First Turn
- Before Completing
- Format Guidelines
- Hot/Cold Split
- File Creation
- Conversation Recall
- Learning Loop
Podgląd SKILL.md
---
name: agent-memory
description: "Repo-local file memory under .scaffolding/ (shared/agent/conversation tiers). TRIGGER when: reading or writing .scaffolding/ memory files, or choosing which file tier an insight belongs in. SKIP: vector memory / MCP search and store (use semantic-memory-mcp); distilling conversations (use distill)."
---
# Agent Memory Protocol
3-tier persistent **file-based** memory under the repo-local `.scaffolding/` directory, for cross-session knowledge accumulation. Vector memory (MCP tools) is covered by the `semantic-memory-mcp` skill.
## Memory Tiers
| Tier | Path | Scope | Written By | Read By |
|------|------|-------|------------|---------|
| **Shared** | `.scaffolding/agent-memory/shared/KNOWLEDGE.md` | Whole project | Any agent | All agents |
| **Agent** | `.scaffolding/agent-memory/agents/{agent-name}/MEMORY.md` | Per agent | Owning agent | Own agent + architect |
| **Conversation** | `.scaffolding/conversations/{conversation_id}/agent-memory/context.md` | Per conversation | Any agent in conversation | Agents in same conversation |
The Conversation tier lives under `.scaffolding/conversations/`, which is a symlink to `<share>/projects/<repo-name>/conversations` (shared across machines). Paths are unchanged; always go through the symlink.
## How Memory Is Read
No hook or pipeline injects these files into agent context -- they are read on demand (see On First Turn). The conversation tier is the inter-agent handoff: a downstream agent in the same chain reads what an upstream agent recorded there.
## On First Turn
Before starting work, read available memory (skip if files don't exist):
1. Read `.scaffolding/agent-memory/shared/KNOWLEDGE.md`
2. Read `.scaffolding/agent-memory/agents/{your-agent-name}/MEMORY.md`
3. If `conversation_id` is provided in task context: Read `.scaffolding/conversations/{conversation_id}/agent-memory/context.md`
## Before Completing
Write significant findings to the appropriate tier:
### Shared Knowledge (KNOWLEDGE.md)
Save here:
- Project architecture facts confirmed across multiple tasks
- Deployment gotchas and infrastructure quirks
- Cross-cutting patterns (e.g. how Redis is used, how tasks flow)
- Known bugs or limitations that affect multiple agents
Do NOT save:
- Agent-specific patterns (use agent memory)
- Task-specific context (use conversation memory)
- Anything already in CLAUDE.md or docs/
### Agent Memory (MEMORY.md)
Save here:
- Patterns specific to your agent's domain (e.g. developer saves coding patterns)
- Lessons learned from mistakes in your domain
- File locations you frequently need
- Recurring debugging insights
Do NOT save:
- Generic project facts (use shared knowledge)
- One-time task details
- Speculative or unverified conclusions
### Conversation Memory (context.md)
Save here:
- Decisions made during this conversation
- Findings from investigation (debugger -> developer handoff)
- Context needed by downstream agents in the same conversation chain
- Original intent and requirements clarifications
Do NOT save:
- Permanent knowledge (use shared or agent memory)
- Raw data or large code snippets
### Read-Only Agents
Agents with `Write` in `disallowedTools` (reviewer, gitops) cannot write to `.scaffolding/agent-memory/` directly. These agents should report findings in their output, and writable agents in the same conversation chain can persist them. Architect has `Write` and may write memory files (only `Edit` is disallowed).
## Format Guidelines
- Max 200 lines per file (keeps the file cheap to read in full)
- Use markdown headers to organize by topic
- Include dates `[YYYY-MM-DD]` for time-sensitive entries
- Tag durable facts with `confidence` (high/medium/low) and `last_verified [YYYY-MM-DD]`; re-verify against live code/config before asserting a stale point-in-time fact, and down-grade or remove ones that no longer hold
- Remove outdated entries proactively
- Use concise bullet points, not prose
## Hot/Cold Split
File-based memory (this skill) is the **hot** layer — read in full on first turn under a 200-line budget, so keep it lean: stable, high-level facts and pointers only. Push detailed prose and rarely-needed, fuzzy-discoverable knowledge to the **cold** layer (vector store) via the `semantic-memory-mcp` skill — it only surfaces on similarity match and carries no per-turn token cost. Durable source-of-truth facts still get a file here; the cold copy is for natural-language recall.
**Local-only carve-out:** secrets and memory/MCP recovery procedures NEVER go to the cold vector store. Recovery info must stay readable when the store itself is down (a 401 means you cannot query the store to learn how to fix it), and secrets must not be embedded in a remote/shared backend. Keep these as file memory only.
## File Creation
If memory files don't exist, create them with the appropriate header:
```markdown
# Shared Knowledge
<!-- Cross-agent project knowledge. Max 200 lines. -->
```
```markdown
# {Agent Name} Memory
<!-- Agent-specific patterns and lessons. Max 200 lines. -->
```
```markdown
# Conversation {conversation_id} Context
<!-- Decisions and findings for this conversation chain. -->
```
## Conversation Recall
Conversation memory is plain files: when a task has a `conversation_id`, read `context.md` yourself (see On First Turn). No database setup is required for conversation-tier memory.
## Learning Loop
The `/learn` command closes the loop between a finished conversation and the
memory tiers above. It distills one conversation into knowledge candidates (via
the `distill` skill's Conversation-Scoped Distillation mode) and routes each
candidate back into this memory system.
### Candidate ingestion into the 3 tiers
| Candidate kind | Target tier | File |
|----------------|-------------|------|
| Cross-cutting project fact | Shared | `.scaffolding/agent-memory/shared/KNOWLEDGE.md` |
| Domain-specific pattern or lesson | Agent | `.scaffolding/agent-memory/agents/{name}/MEMORY.md` |
| Decision relevant only to the active chain | Conversation | `.scaffolding/conversations/{id}/agent-memory/context.md` |
Ingestion is **propose-then-confirm**: `/learn` prints the proposed memory diff
and applies it only on explicit confirmation. Writes respect the 200-line
`KNOWLEDGE.md` limit — overflow routes to the most relevant agent file per the
`distill` overflow rule. Applied entries are picked up by agents that read the files on the next
task.
### Escalation to /create-skill
If a candidate is a **repeatable procedure** rather than a situational fact (per
`distill`'s Skill Promotion Criterion), it is not written to memory. Instead
`/learn` proposes a `/create-skill` invocation with a pre-filled draft, escalating
the knowledge into a first-class auto-invokable skill. Memory holds facts; skills
hold reusable how-to procedures.
Wersje
| Repozytorium | Wynik | Licencja |
|---|---|---|
| Ta strona · komluk/scaffolding | 100 | MIT |
| TerminalSkills/skills | 100 | Apache-2.0 |
| nirholas/three.ws | 100 | Apache-2.0 |
| nimadorostkar/Claude-Skills-collection | 100 | MIT |
| alirezarezvani/claude-skills | 100 | MIT |
| norifumi3/cc-marketplace | 100 | MIT |
| OpenHands/extensions | 92 | MIT |
| HelixDevelopment/agent | 92 | MIT |
| VoDaiLocz/kilo-kit-mcp | 90 | Apache-2.0 |
Migawka bazy z 13.11.2026 · wersja paczki 83a2e632bd24 (skrót SHA-256 całej paczki)
Pobrania w ostatnich 30 dniach: 1 · ranking
Zgłoś problem z tym skillem: szkodliwa treść, błędny opis albo prośba autora o usunięcie.
Podobne skille
- 100semantic-memory-mcp
Wyszukuje, przywołuje i zapisuje wnioski w pamięci MCP podczas zadania, a także decyduje, czy notatkę warto zapisać. - 100skill-authoring
Opisuje metodykę pisania skilli zgodnych z szablonem: kontrakt frontmatter, struktura treści i walidacja, gdy decydujesz o nowym skillu. - 90memory-design
Projektuje pamięć agenta LLM: co zachować, gdzie to przechowywać i kiedy pamięć szkodzi bardziej, niż pomaga, z porównaniem Mem0 i Letta. - 95claw-memory-management
Prowadzi pamięć roboczą agenta: warstwy, zasady zapisu, format wpisów i konserwację plików memory oraz MEMORY.md. - 100evolve
Obsługuje pamięć międzysesyjną evolve opartą na Honcho: przypomina, co wiadomo o użytkowniku lub skillu, zapisuje trwałe fakty i wskazuje, do której warstwy pamięci trafia dana wiedza. - 100advanced-memory-skill-creator
Planuje, tworzy szkielety, waliduje i pakuje skille Claude w Advanced Memory MCP.