Ar9av/obsidian-wiki / skills/hermes-history-ingest
hermes-history-ingest
VerifiedIngest Hermes agent history into Obsidian as distilled knowledge. Use for importing or mining ~/.hermes sessions, memories, or logs; use wiki-agent for targeted topic-only cross-agent recall.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 9.3 KB |
| references/hermes-data-format.md | markdown | 3.0 KB |
references/hermes-data-format.md
View on GitHub# Hermes Agent — Data Format Reference
Field-level notes for parsing `~/.hermes/` artifacts during wiki ingest.
## Cache Root
`~/.hermes/` — or `$HERMES_HOME` for non-default profiles. All paths below are relative to this root.
## memories/
Each file is one discrete memory the agent persisted.
### Markdown memories (`*.md`)
Optional YAML frontmatter, then prose body:
```markdown
---
tags: [python, async, debugging]
created_at: 2026-03-10T14:22:00Z
project: my-api
---
When using `asyncio.gather` with return_exceptions=True, failed tasks return the exception
object rather than raising — check `isinstance(result, Exception)` on each item.
```
Fields of interest:
- `tags` — maps directly to wiki tags; normalize to kebab-case
- `created_at` — use for provenance / journal category decisions
- `project` — route to `projects/<project>/` when set
### JSON memories (`*.json`)
```json
{
"content": "...",
"created_at": "2026-03-10T14:22:00Z",
"tags": ["python", "async"],
"project": "my-api",
"source": "session:abc123"
}
```
Same field semantics as the markdown variant. `source` links back to the originating session.
## sessions/
Present only when session logging is enabled (`config.yaml: logging.sessions: true`).
### Directory layout
```
sessions/
└── 2026-03-10/
└── abc123.jsonl
```
### JSONL line schemas
**User / assistant turns:**
```json
{"role": "user", "content": "How do I debounce a React input?"}
{"role": "assistant", "content": "Use useCallback + useEffect with a setTimeout..."}
```
**Tool use:**
```json
{
"type": "tool_use",
"id": "tu_abc",
"name": "read_file",
"input": {"path": "/home/ubuntu/project/src/App.tsx"}
}
```
**Tool result:**
```json
{
"type": "tool_result",
"tool_use_id": "tu_abc",
"content": "..."
}
```
**Session metadata (first line):**
```json
{
"type": "session_meta",
"id": "abc123",
"cwd": "/home/ubuntu/projects/my-app",
"model": "claude-sonnet-4-6",
"started_at": "2026-03-10T14:00:00Z"
}
```
`cwd` is the most reliable project inference signal — use it to route knowledge to the right `projects/<name>/` page.
## config.yaml
Rarely useful for ingest. Useful fields if needed:
```yaml
model: claude-sonnet-4-6
hermes_home: ~/.hermes # resolved path, respects $HERMES_HOME
logging:
sessions: true # whether session JSONL files are written
memories: true # whether memories are persisted
```
## .hub/
Skills Hub state. **Skip entirely during ingest.** Contains:
- `lock.json` — installed skill manifest (not user knowledge)
- `audit.log` — install/update history
- `quarantine/` — flagged skills awaiting review
## Extraction Priority
| Source | Signal | Noise |
|---|---|---|
| `memories/*.md` | High — curated, stable | Low |
| `memories/*.json` | High — structured | Low |
| `sessions/**/*.jsonl` — assistant turns | Medium | Medium |
| `sessions/**/*.jsonl` — tool pairs | Low | High |
| `config.yaml` | Very low | — |
| `.hub/` | None | — |
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |