ar9av/obsidian-wiki

hermes-history-ingest

Ingest Hermes agent history into Obsidian as distilled knowledge.

소스 보기

사용 방법

  1. 설치 명령을 복사하고 자신의 에이전트 환경에 설치하기 전에 소스 패키지를 확인하세요.
  2. 필요한 도구, 인증 정보, 지원 환경은 원본 문서에서 확인하세요.
  3. 입력과 원하는 산출물을 설명하고 출처와 결과를 대조하세요.
npx skills add https://github.com/ar9av/obsidian-wiki --skill hermes-history-ingest

시작 전 확인

  • 설치에는 모델 구독, API 한도, 파일 접근 권한이 포함되지 않습니다.
  • 별점 수와 설치 수는 활동 지표이며 독립적인 품질·보안 검증이 아닙니다.
원본 Skill 문서

원본 저장소의 제목, 예시, 코드, 표, 링크, 이미지를 유지해 표시합니다.

Hermes History Ingest — Conversation & Memory Mining

You are extracting knowledge from the user's Hermes agent history and distilling it into the Obsidian wiki. Hermes stores both free-form memories and structured session transcripts — focus on durable knowledge, not operational telemetry.

This skill can be invoked directly or via the wiki-history-ingest router (/wiki-history-ingest hermes).

Before You Start

Writing profile: Before drafting or rewriting natural-language Markdown, read and apply the Writing Profile Resolution section in llm-wiki/SKILL.md. Framework schema, provenance, safety, and operation-specific requirements take precedence. WRITING.md preferences apply only to newly drafted or rewritten natural-language Markdown; preserve source content and structured records.

  1. Resolve config — follow the Config Resolution Protocol in llm-wiki/SKILL.md (inline @name override → walk up CWD for .env → global config → prompt setup). This gives OBSIDIAN_VAULT_PATH and HERMES_HISTORY_PATH (defaults to ~/.hermes)
  2. Read .manifest.json at the vault root to check what has already been ingested
  3. Read index.md at the vault root to understand what the wiki already contains

Ingest Modes

Append Mode (default)

Check .manifest.json for each source file. Only process:

  • Files not in the manifest (new memory files, new session logs)
  • Files whose modification time is newer than ingested_at in the manifest

Use this mode for regular syncs.

Full Mode

Process everything regardless of manifest. Use after wiki-rebuild or if the user explicitly asks for a full re-ingest.

Hermes Data Layout

Hermes stores all local artifacts under ~/.hermes/ (or $HERMES_HOME for non-default profiles).

~/.hermes/
├── memories/                          # Persistent agent memories (markdown or JSON)
│   └── *.md / *.json
├── skills/                            # Installed skills (read-only for ingest purposes)
│   └── <skill-name>/SKILL.md
├── sessions/                          # Session transcripts (if session logging is enabled)
│   └── YYYY-MM-DD/
│       └── <session-id>.jsonl
├── config.yaml                        # User config (model, theme, paths)
└── .hub/                              # Skills Hub state (lock.json, audit.log, quarantine/)

Key data sources ranked by value

  1. memories/*.md / memories/*.json — highest signal; curated persistent knowledge the agent accumulated
  2. sessions/**/*.jsonl — structured turn-by-turn transcripts; rich but noisy
  3. config.yaml — metadata only (model preferences, paths); rarely worth ingesting

Skip .hub/ internals (audit/quarantine state) and the skills/ directory (source material, not user knowledge).

Step 1: Survey and Compute Delta

Scan HERMES_HISTORY_PATH and compare against .manifest.json:

  • ~/.hermes/memories/
  • ~/.hermes/sessions/**/ (if present)

Classify each file:

  • New — not in manifest
  • Modified — in manifest but file is newer than ingested_at
  • Unchanged — already ingested and unchanged

Report a concise delta summary before deep parsing.

Step 2: Parse Memories First

Memories are the highest-value source. Hermes writes them as either:

  • Markdown — structured prose with optional frontmatter; ingest directly
  • JSON — {"content": "...", "created_at": "...", "tags": [...]} records

For each memory:

  • Extract the core knowledge claim
  • Note any tags Hermes attached (they often map to wiki categories)
  • Merge into the appropriate wiki page rather than creating one memory = one page

Step 3: Parse Session JSONL Safely

Each session JSONL line is an event envelope. Common shapes:

json
{"role": "user", "content": "..."}
{"role": "assistant", "content": "..."}
{"type": "tool_use", "name": "...", "input": {...}}
{"type": "tool_result", "content": "..."}

Extraction rules

  • Prioritize assistant responses that state conclusions, patterns, or decisions
  • Extract user intent from high-signal turns; skip low-information follow-ups
  • Treat tool_use / tool_result pairs as context, not primary content
  • Skip token accounting, internal plumbing, and repeated plan echoes

Critical privacy filter

Session logs can include injected instructions, tool payloads, and sensitive text. Do not ingest verbatim.

  • Remove API keys, tokens, passwords, credentials
  • Redact private identifiers unless relevant and user-approved
  • Summarize; do not quote raw transcripts verbatim

Step 4: Cluster by Topic

Do not create one wiki page per memory or session.

  • Group memories by stable topic (concept, tool, project, technique)
  • Split mixed sessions into separate themes
  • Merge recurring patterns across dates and projects
  • Use file paths or session cwd metadata to infer project scope when available

Step 5: Distill into Wiki Pages

Dates: follow wiki-ingest's event-time rules. Resolve relative dates ("yesterday", "last week") against the session/message timestamp, never today, and when a newer session contradicts an existing page, invalidate the old claim (## History or valid_until + superseded_by) rather than overwriting it.

Route extracted knowledge using existing wiki conventions:

  • Project-specific architecture/process → projects/<name>/...
  • General concepts → concepts/
  • Recurring techniques/debug playbooks → skills/
  • Tools/services/frameworks → entities/
  • Cross-session patterns → synthesis/

For each impacted project, create/update projects/<name>/<name>.md.

Writing rules

  • Distill knowledge, not chronology
  • Avoid "on date X we discussed..." unless date context is essential
  • Add summary: frontmatter on each new/updated page (1–2 sentences, ≤ 200 chars)
  • Add confidence and lifecycle fields to every new page:
yaml
  base_confidence: 0.42
  lifecycle: draft
  lifecycle_changed: <obsidian-wiki memory now --date>

Leave lifecycle unchanged on update.

  • Add provenance markers:
  • ^[extracted] when directly grounded in explicit memory/session content
  • ^[inferred] when synthesizing patterns across multiple memories
  • ^[ambiguous] when memories conflict
  • Add/update provenance: frontmatter mix for each changed page

Step 6: Update Manifest, Log, and Index

Update .manifest.json

For each processed source file:

  • ingested_at, size_bytes, modified_at
  • source_type: hermes_memory | hermes_session
  • project: inferred project name (when applicable)
  • pages_created, pages_updated

Add/update a top-level summary block:

json
{
  "hermes": {
    "source_path": "~/.hermes/",
    "last_ingested": "TIMESTAMP",
    "memories_ingested": 42,
    "sessions_ingested": 7,
    "pages_created": 5,
    "pages_updated": 12
  }
}

Update special files

Update index.md, log.md, and hot.md with one locked call:

bash
obsidian-wiki memory sync HERMES_HISTORY_INGEST \
  memories=<memories> sessions=<sessions> pages_updated=<pages_updated> \
  pages_created=<pages_created> mode=<mode> \
  --takeaways "Ingested 42 Hermes memories and 7 sessions; dominant themes: reasoning strategies, tool use patterns." --expect-takeaways-sha256 "$TAKEAWAYS_REVISION"

Never hand-edit index.md, log.md, or hot.md — the command takes the lock that keeps a parallel writer from dropping your update. --takeaways is the one-line conceptual summary that used to go in Recent Activity; omit it to leave the previous takeaways untouched.

See skills/llm-wiki/references/MEMORY.md for the full procedure.

Privacy and Compliance

  • Distill and synthesize; avoid raw memory or transcript dumps
  • Default to redaction for anything that looks sensitive
  • Ask the user before storing personal or sensitive details
  • Keep references to other people minimal and purpose-bound

Reference

See references/hermes-data-format.md for field-level notes and extraction guidance.

QMD Refresh After Vault Writes

QMD is a search index, not the source of truth. If $QMD_WIKI_COLLECTION is empty or unset, skip this step. Run it only after this skill has written or rewritten vault markdown. If QMD refresh fails, do not roll back the vault changes; report the QMD status separately.

Use $QMD_CLI if set; otherwise use qmd.

bash
${QMD_CLI:-qmd} update

If the output says vectors are needed or embeddings may be stale, run:

bash
${QMD_CLI:-qmd} embed

Verify the collection with either:

bash
${QMD_CLI:-qmd} ls "$QMD_WIKI_COLLECTION"

or, when a specific page path is known:

bash
${QMD_CLI:-qmd} get "qmd://$QMD_WIKI_COLLECTION/<page>.md" -l 5

Record one of:

  • QMD refreshed: update + embed + verified
  • QMD refreshed: update only + verified
  • QMD skipped: QMD_WIKI_COLLECTION unset
  • QMD skipped: qmd CLI unavailable
  • QMD failed: <short error summary>

Before explicit takeaway replacement, read/reconcile the full current Key Takeaways and obtain TAKEAWAYSREVISION from hot.takeawayssha256 in memory status --json (llm-wiki/references/MEMORY.md). Preserve still-valid owner conclusions. Omit --takeaways for mechanical bookkeeping; stale revisions require review, not blind retry.

같은 저장소의 Skills

더 많은 Skills

모든 Skills
ar9av
커뮤니티

skill-creator

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

1시간 설치 수
1
GitHub Stars
3.8천
업데이트
11월 21일
ar9av
커뮤니티

copilot-history-ingest

Ingest GitHub Copilot CLI/session history into Obsidian as distilled knowledge. Use for importing or mining Copilot history; not for general Copilot help, simple session search, or backup.

1시간 설치 수
1
GitHub Stars
3.8천
업데이트
11월 20일
ar9av
커뮤니티

memory-bridge

Browse or compare wiki knowledge by originating AI tool. Use for cross-tool memory questions, tool-specific knowledge, or gap/diff analysis between Codex, Claude, Hermes, and other agents.

1시간 설치 수
1
GitHub Stars
3.8천
업데이트
11월 20일
ar9av
커뮤니티

vault-skill-factory

Create a reviewable Agent Skill package from mature curated wiki pages, or from one recorded walkthrough of a job (a narrated screen recording, a call, a voice note: "turn this recording into a skill", "I did it once out loud, make it a skill"). Use when turning verified vault knowledge or a recorded workflow into a reusable skill. Reads the vault and writes only to a review directory; it does not install skills.

1시간 설치 수
1
GitHub Stars
3.8천
업데이트
11월 20일