Show HN: Shivvr – Ephemeral semantic embedding and cognitive agent service

Shivvr, an ephemeral semantic embedding and cognitive agent service, launched on Show HN, offering chunking, embedding with GTR-T5-base, hybrid FST-BM25 search, and turn-based agent reasoning via Model Context Protocol (MCP). The service supports zero-config integration with Claude Code, Antigravity, and Codex, and provides per-agent orthogonal matrix rotation on embeddings for encryption.

Ephemeral semantic embedding & cognitive agent service. Chunk text. Embed with GTR-T5-base. Search via hybrid FST-BM25 vector rank fusion. Stream turn-based cognitive agent reasoning via native Model Context Protocol MCP . Sentence-boundary chunking + GTR-T5-base embeddings 768d . Stores in RwLock<HashMap — pure ephemeral compute. RRF blending dense vectors and sparse lexical indices. FST dictionary scanning provides microsecond safe query guardrails and intent-entity score boosting. Turn-based agent loop with integrated memory search, document ingestion, session indexing, and sandboxed command execution. Powered by OpenAI/Anthropic. Complete Model Context Protocol HTTP/SSE server endpoint /mcp/sse allowing immediate, zero-config integration with Claude Code, Antigravity, and Codex. Per-agent orthogonal matrix rotation on embeddings. Cosine similarity preserved under encryption. Keys are in-memory only. organize role uses GTR-T5-base 768d . retrieve role uses OpenAI text-embedding-ada-002 1536d — pass your own key or set server-side. | Method | Endpoint | Description | |---|---|---| | GET | /health | Status, model info, live counts | | GET | /mcp/sse | MCP Server SSE handshake | | POST | /mcp/message | MCP Server JSON-RPC message router | | POST | /sessions/:id/agent/chat | Stream non-blocking GhostAgent cognitive turns SSE | | POST | /sessions/:id/ingest | Chunk + embed text into session | | GET | /sessions/:id/search?q=... | Semantic search supports RRF hybrid & lexical only | | GET | /sessions/:id | Session metadata | | DELETE | /sessions/:id | Delete session | | GET | /temp | List temp stores with TTL | | POST | /temp/:name/ingest | Ingest into temp store 2 hr TTL | | GET | /temp/:name/search?q=... | Search temp store | | DELETE | /temp/:name | Delete temp store | | POST | /agent/:id/register | Register per-agent orthogonal key | | POST | /agent/:id/encrypt | Encrypt embeddings | | POST | /agent/:id/decrypt | Decrypt embeddings | | POST | /invert | Reconstruct text from embedding vector | Ingest into session curl -X POST https://shivvr.nuts.services/sessions/my-session/ingest \ -H "Content-Type: application/json" \ -d '{"text": "Supreme Raven is protected by Known Opossum.", "source": "vault specs"}' Autonomous Agent Conversational Chat Streams Thoughts, ToolCalls, & Answer via SSE curl -i -X POST http://localhost:8085/sessions/my-session/agent/chat \ -H "Content-Type: application/json" \ -d '{"message": "Who protects the Supreme Raven?"}' Vector-Lexical Hybrid RRF Search curl "http://localhost:8085/sessions/my-session/search?q=Known+Opossum&hybrid=true" High-speed Lexical-Only BM25 Search Bypasses ONNX embedder curl "http://localhost:8085/sessions/my-session/search?q=Opossum&lexical only=true" Synchronize Claude Code or Antigravity with shivvr's Native MCP Server nemesis8 mcp add http://localhost:8085/mcp/sse | Param | Default | Description | |---|---|---| q | required | Query text | n | 5 | Number of results | hybrid | false | Blend semantic vectors + BM25 scores Reciprocal Rank Fusion | lexical only | false | Bypass vector embedder, execute pure BM25 search | guardrail | true | Enable FST toxic term scanning and automatic query blocking | role | organize | organize 768d local or retrieve 1536d OpenAI | time weight | 0.0 | Blend semantic + recency score 0–1 | decay halflife hours | 168 | Recency decay half-life in hours | include nearby | false | Return temporally adjacent chunks | agent id | — | Agent ID for encrypted search | openai api key | — | Per-request OpenAI key for retrieve role overrides server key | | Variable | Default | Description | |---|---|---| PORT | 8080 | Listen port | MODEL PATH | models/gtr-t5-base.onnx | GTR-T5-base ONNX embedder | TOKENIZER PATH | models/tokenizer.json | Tokenizer | OPENAI API KEY | — | Enables OpenAI completions and retrieve embeddings | ANTHROPIC API KEY | — | Enables Anthropic completions and GhostAgent loops | NUTS AUTH JWKS URL | — | Enable auth open dev mode if unset | NUTS AUTH VALIDATE URL | https://auth.nuts.services/api/validate | API token validation endpoint | | Layer | Choice | |---|---| | Runtime | Rust + Tokio + axum | | Cognition | GhostAgent cognitive RAG turn loop OpenAI / Anthropic compat | | MCP Server | HTTP/SSE JSON-RPC 2.0 Model Context Protocol transport layer | | Hybrid Index | Tantivy FST deterministic phrase engine + BM25F field indexer | | Embedding | GTR-T5-base 768d via ONNX Runtime 2.0 — local, required | | Storage | Ephemeral RwLock<HashMap — no disk, no volume mounts | | GPU | CUDA 12.6 via ort EP on Cloud Run L4 — CPU fallback automatic | | Inversion | vec2text gtr-base projection + T5 enc/dec — optional |