Look up a cached result by key. Returns the stored value if found, with trust score.

Use this BEFORE computing expensive results -- another agent may have already computed and cached the answer, saving tokens and latency.

Higher trust_score = more agents have verified this result is accurate.

Args: key: Cache key (e.g. 'weather:berlin:2026-03-28', 'research:quantum-computing') agent_id: Your agent identifier for analytics tracking

Search the shared cache by keywords. Find relevant cached results from other agents.

Search before computing -- if another agent has cached a similar result, you can reuse it directly. Results include trust scores showing verification level.

Args: query: Keywords to search for (e.g. 'weather berlin', 'bitcoin price') limit: Max number of results to return (default: 10, max: 50)

Store a computed result in the shared cache so other agents can reuse it.

After computing an expensive result (web search, analysis, API call), store it here. Other agents will find it via cache_lookup or cache_search.

The entry starts with trust_score=1 (you as the first confirmer). Other agents can use confirm_entry to increase the trust score.

Args: key: Unique cache key (e.g. 'weather:berlin:2026-03-28', 'summary:arxiv:2501.00001') value: The result to cache (JSON string, text, or any serializable content) ttl_seconds: Time-to-live in seconds (default: 86400 = 24h, max: 604800 = 7 days) tags: Comma-separated tags for discovery (e.g. 'weather,berlin,temperature') agent_id: Your agent identifier for attribution (e.g. 'weather-agent-v2')

Confirm a cached result is accurate. Increases the entry's trust score.

When you use a cached result and verify it's correct, confirm it. This builds trust for other agents: entries confirmed by multiple agents are more reliable than unverified ones.

NETWORK EFFECT: More agents confirming = higher trust = more reuse.

Each agent can confirm an entry once. Duplicate confirmations are ignored.

Args: key: Cache key to confirm (e.g. 'weather:berlin:2026-03-28') agent_id: Your agent identifier (e.g. 'research-agent-v1')

Get only cache entries confirmed by multiple agents (high trust).

Returns entries with trust_score >= min_trust, sorted by trust score. These are the most reliable cached results -- verified by multiple independent agents.

Use this to find the most trustworthy precomputed results available.

Args: min_trust: Minimum trust score required (default: 3 = confirmed by 3+ agents) limit: Max entries to return (default: 20)

Detailed analytics about cache usage, trust, and network effects.

Shows: hit rate, most accessed entries, most trusted entries, top contributing agents, trust distribution, and network effect score.

Use this to understand how the shared cache is performing and how strong the network effect has become.

Get basic statistics about the shared cache -- hits, misses, top queries.

For more detailed analytics including trust scores and network effects, use cache_analytics instead.

List available cache entries with trust scores, optionally filtered by tags.

Browse what other agents have cached. Entries include trust scores showing how many agents have verified each result.

Args: limit: Max entries to return (default: 20, max: 100) tags: Filter by tags, comma-separated (e.g. 'weather,temperature')