Build integrated IS/BS/CF financial workbooks in Excel.
日本語の概要は準備中です。原文の説明を表示しています。
Use for session compression and full-text search.
インストール方法を見るインストールする前に、エージェントに与えられる指示の中身を確認できます。
Intelligente Session-Komprimierung aus der OpenAmer state.db:
$OPENAMER_HOME\scripts\context-compressor.py$OPENAMER_HOME\context-compressor\archives\$OPENAMER_HOME\context-compressor\index.json| Flag | Beschreibung |
|---|---|
--session <id> | Einzelne Session komprimieren → JSON on stdout |
--batch [Tage] | Alle Sessions älter als N Tage archivieren (default: 7) |
--stats | Kompressionsrate + Extraktions-Statistiken anzeigen |
--search <query> | Volltextsuche in allen komprimierten Sessions |
# Einzelne Session komprimieren
python scripts/context-compressor.py --session 20260821_233243_387822
# Batch-Verarbeitung (alle Sessions >7 Tage)
python scripts/context-compressor.py --batch
# Alle Sessions verarbeiten (auch aktuelle)
python scripts/context-compressor.py --batch 0
# Statistiken anzeigen
python scripts/context-compressor.py --stats
# Volltextsuche
python scripts/context-compressor.py --search "API-Key"
python scripts/context-compressor.py --search "entscheidung"
{
"session_id": "20260821_233243_387822",
"title": "...",
"raw_chars": 59414,
"compressed_chars": 4756,
"compression_percent": "92.0%",
"decisions": ["..."],
"action_items": ["..."],
"learnings": ["..."],
"open_points": ["..."],
"messages": [
{"id": 24014, "role": "user", "compressed": "...", "original_len": 89, "compressed_len": 89},
{"id": 24016, "role": "tool", "compressed": "[JSON] keys=[...]", "original_len": 8125, "compressed_len": 221}
]
}
<antthinking>, <tool_call>, lange Code-Blöcke[JSON] keys=[...] (auf Schlüssel reduziert)OPENAMER_HOME (default: $OPENAMER_HOME\state.db)sessions, messagescontext-compressor/archives/batch_<timestamp>.jsonまだレビューはありません。使ってみた感想をお寄せください。
概要と使いどころ
Build integrated IS/BS/CF financial workbooks in Excel.
日本語の概要は準備中です。原文の説明を表示しています。
Run and grow the OpenAmer Agent-to-Agent swarm: identity, trust, node-to-node ask, signed skill/insight sharing, and the autonomous self-learning loop.
日本語の概要は準備中です。原文の説明を表示しています。
Use for A/B experiments on OpenAmer configs and skills.
日本語の概要は準備中です。原文の説明を表示しています。
Roleplay a hostile user to find and triage UX pain points.
日本語の概要は準備中です。原文の説明を表示しています。
Agent mesh: master/worker nodes, HTTP delegation, heartbeat.
日本語の概要は準備中です。原文の説明を表示しています。
Use for agentic commerce payments tasks. Candidate synthesized from trend radar; awaiting trial promotion.
日本語の概要は準備中です。原文の説明を表示しています。