English | 中文
Deepsiper Enthea (deepsiper-enthea) is a sovereign, agent-driven LLM evaluation harness forked from deepseek-ai/deepseek-harness (dsh 0.1.0-rc.7). It provides end-to-end multi-model orchestration, self-hosted and sovereign backend integration, Cordis-powered extensible plugin pipelines, and JSON-RPC automation for modern LLM evaluation workflows.
- Sovereign Backend: Native integration with EntheAI and self-hosted inference nodes with zero external data leakage.
- ULTRA-LSP in core: Language-server code intelligence (
goToDefinition,findReferences,goToImplementation,hover) shipped in thedsh-basecore bundle with a TypeScript/JavaScript stdio provider, so thelsptool is available in every profile. - Evaluation Plugins: Pluggable evaluation suites including
tool-eval,eval-entheai, and custom benchmarking metrics. - OpenCode Bridge & JSON-RPC SDK: Drive evaluation runs and automated agent loops programmatically from OpenCode or custom orchestrators.
- Multi-Model Orchestration: Unified provider interfaces for DeepSeek, Gemini, local models, and any OpenAI-compatible endpoint.
- Granular Sandboxing & Telemetry: Native Landlock isolation, deterministic replay, and structured session persistence.
Everything in Deepsiper Enthea is a composable Cordis plugin.
┌─────────────────────────────────────┐
│ OpenCode / JSON-RPC / CLI / Web │
└──────────────────┬──────────────────┘
│
┌──────────────────▼──────────────────┐
│ Cordis Kernel (Context & DI) │
└────┬──────────────┬───────────────┬─┘
│ │ │
┌──────────────▼─────┐ ┌──────▼──────┐ ┌──────▼──────────────┐
│ Sovereign Backends│ │ Eval Plugins│ │ Sandboxed Tool Seams│
│ (EntheAI / Local) │ │ (tool-eval) │ │ (Landlock / Bash) │
└────────────────────┘ └─────────────┘ └─────────────────────┘
- Runtime & Language: Node.js
>=22.19.0or>=24.0.0, TypeScript 6 (Strict ESM) - Bundler & Build:
tsdown/rolldown+tscproject references - Testing & Quality: Vitest 4, Oxlint, JSCPD clone detection
- Plugin Kernel: Vendored Cordis framework with spatiotemporal composability
- Node.js
^22.19.0 || >=24.0.0 pnpm >= 11.0.0
# Clone repository
git clone https://github.com/8b-is/deepsiper-enthea.git
cd deepsiper-enthea
# Install dependencies and build harness
pnpm install
pnpm buildDeepsiper Enthea includes an automated multi-case AST evaluation harness (examples/eval-entheai/driver/benchmark_sweep.py) verifying mathematical precision, algorithm syntax, and zero reward-hacking across isolated execution environments:
| Benchmark Task | Category | Trials | Pass Rate | Mean Latency |
|---|---|---|---|---|
| FizzBuzz Logic & 18 Edge Cases | Logic Verification | 2 / 2 | 100.0% | ~16.8 s |
| Mathematical Exponentiation | 2 / 2 | 100.0% | ~16.1 s | |
| Kademlia 256-bit XOR Metric Distance | Distributed DHT Routing | 2 / 2 | 100.0% | ~12.8 s |
| BitLinear |
Ternary Weight Mapping | 2 / 2 | 100.0% | ~13.9 s |
| AST Invariant & Pure Syntax Validator | Syntax Tree Verification | 2 / 2 | 100.0% | ~13.6 s |
# Keyless fast gate (no dsh runtime): grading logic + canonical validator
pnpm bench:entheai:verify
# Full multi-case sweep against the built dsh runtime (inline stub backend)
pnpm bench:entheai- Getting Started Guide
- Architecture & Plugin Seams
- Writing Custom Plugins
- JSON-RPC SDK
- Sovereign Backends (EntheAI)
- Design System Spec
- Fork Origin: 8b-is/deepsiper-enthea
- Upstream: deepseek-ai/deepseek-harness
- Organization: 8b-is
- Axiom Quant (Monograph & Proofs):
https://axiomquant.org - Classroom SOTA Training (Council of Elders):
https://github.com/8b-is/classroom-sota-training - Honest-IRC / EtherHive (PQC Messaging):
https://github.com/peterlodri-sec/etherhive·https://etherhive.vaked.dev - Lovetta Lane Constellation Portal:
https://vaked.dev - Personal Hub:
https://peterl.dev - Bluesky:
@0xp3t3rl.bsky.social
MIT © 8b-is & DeepSeek AI contributors. Third-party dependency notices are listed in THIRD_PARTY_NOTICES.md.
Genesis Seal: 7c242080f5f821e5eaf563fe2208d60632c451687baf65f4fe8e4a0d226e3ecf · WE. {-1, 0, +1}. <3