Agent RecallPersistentes Gedächtnis für KI-Coding-Agenten

1. Installieren

pip install 'agent-recall[mcp]'
agent-recall init

2. In den Editor einbinden

.mcp.json (Claude Code, Cline) oder Editor-Einstellungen (Cursor, Windsurf)

{
  "mcpServers": {
    "memory": {
      "command": "python3",
      "args": ["-m", "agent_recall.mcp_server"]
    }
  }
}

3. Auto-Briefing-Hook

.claude/settings.json. Lädt das Briefing beim Session-Start.

{
  "hooks": {
    "SessionStart": [{
      "hooks": [{
        "type": "command",
        "command": "agent-recall-session-start"
      }]
    }],
    "PostToolUse": [{
      "matcher": "mcp__memory__.*",
      "hooks": [{
        "type": "command",
        "command": "agent-recall-post-tool-use"
      }]
    }]
  }
}

4. Prüfen

agent-recall status

Database: ~/.agent-recall/frames.db
Entities: 27
  client: 11, person: 8, company: 1
  concept: 2, entity: 3, topic: 2

from agent_recall import MemoryStore, ScopedView

with MemoryStore() as store:
    alice = store.resolve_entity("Alice", "person")
    store.set_slot(alice, "role", "Lead Engineer", scope="acme")
    store.add_observation(alice, "Prefers async", scope="acme")

    view = ScopedView(store, ["global", "acme"])
    entity = view.get_entity("Alice")
    print(entity["slots"]["role"])  # "Lead Engineer"

    # Suche, Historie, Transaktionen
    results = store.search("engineer")
    store.set_slot(alice, "role", "Staff Engineer", scope="acme")
    history = store.get_slot_history(alice, "role")

    with store.transaction():
        bob = store.resolve_entity("Bob", "person")
        store.set_slot(bob, "role", "PM")

YAML-Konfiguration für mehrere Agenten

hierarchy:
  agency:
    - client-a
    - client-b

briefing:
  backend: cli
  model: opus
  adaptive: true
  auto_discover: true

agents:
  coordinator:
    model: opus
    output_budget: 12000
  client-a:
    template: client
    context_files:
      - docs/client-a-brief.md

Bring Your Own LLM

from agent_recall import generate_briefing, LLMResult

def my_llm(prompt, model, timeout):
    response = call_your_api(prompt)
    return LLMResult(
        text=response.text,
        input_tokens=0,
        output_tokens=0
    )

generate_briefing(
    "my-agent",
    llm_caller=my_llm,
    force=True
)