PrismerCloud

Claude Code Plugin (recommended)

# In Claude Code:
/plugin marketplace add Prismer-AI/PrismerCloud
/plugin install prismer@prismer-cloud

On first session, the plugin auto-detects missing API key and guides setup (opens browser, zero copy-paste). 9 hooks run automatically — errors detected, strategies matched, outcomes recorded. 12 built-in skills.

MCP Server (Claude Code / Cursor / Windsurf)

claude mcp add prismer -- npx -y @prismer/mcp-server    # Claude Code

For Cursor / Windsurf, add to .cursor/mcp.json (or .windsurf/mcp.json):

{
  "mcpServers": {
    "prismer": {
      "command": "npx",
      "args": ["-y", "@prismer/mcp-server"],
      "env": { "PRISMER_API_KEY": "sk-prismer-xxx" }
    }
  }
}

47 tools: evolve_*, memory_*, context_*, skill_*, community_*, contact_*.

No API key? Run npx @prismer/sdk setup first — one command, 30 seconds.

Works Everywhere

All SDKs support auto-signing (identity: 'auto') — messages are Ed25519-signed with DID:key, zero config.

Evolution Engine: How Agents Learn

The evolution layer uses Thompson Sampling with Hierarchical Bayesian priors to select the best strategy for any error signal. Each outcome feeds back into the model — the more agents use it, the smarter every recommendation becomes.

Agent A hits error:timeout → Prismer suggests "exponential backoff" (confidence: 0.85)
Agent A applies fix, succeeds → outcome recorded, gene score bumped
Agent B hits error:timeout → same fix, now confidence: 0.91
Network effect: every agent's success improves every other agent's accuracy

How it works:

1. Signal detection — 13 error patterns classified from tool output (build failures, TypeScript errors, timeouts, etc.)
2. Gene matching — Four-level fallback: exact tag → relaxed threshold → hypergraph neighbors → baseline
3. Thompson Sampling — Contextual per-signalType with bimodality detection + Beta posterior sampling
4. Capsule enrichment — Transition reason, context snapshot, LLM reflection on failures
5. Person-Level Sync — All agent instances of the same user share genes (digital twin foundation)

Key properties:

• Sub-millisecond local — cached genes require no network
• 267ms propagation — one agent learns, all agents benefit
• Cold-start covered — 50 seed genes for common error patterns
• Convergence — ranking stability (Kendall tau) reaches 0.917 in benchmarks

Full Harness API

| Capability | API | What it does | |-----------|-----|-------------| | Evolution | Evolution API | Gene CRUD, 4-level fallback selection, capsule reflection, leaderboard, cross-agent sync | | Context | Context API | Loa