mirror of
https://github.com/open-jarvis/OpenJarvis.git
synced 2026-07-30 10:52:15 +00:00
Jon Saad-FalconandClaude Opus 4.6
323d7ff032
- Eval config: TOML-based suite configs defining models x benchmarks matrix, loaded via --config flag. Includes load_eval_config(), expand_suite(), 7 config dataclasses, 3 example configs, and 61 new tests. - Pillar-aligned config: generation params in IntelligenceConfig, nested engine/learning configs, agent objective/system_prompt/context_from_memory, structured learning sub-policies, TOML migration layer. - Documentation: evaluations user guide, evals API reference, updated mkdocs.yml navigation, updated architecture docs. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
1.5 KiB
1.5 KiB
API Reference
This section contains the auto-generated API reference for the OpenJarvis Python package. Documentation is extracted directly from the source code docstrings using mkdocstrings.
Each page documents a major module of the framework, including abstract base classes, concrete implementations, and utility functions.
Modules
| Module | Description |
|---|---|
| SDK | High-level Jarvis class and MemoryHandle proxy |
| Core | Registries, types, configuration, and event bus |
| Engine | Inference engine ABC and backends (Ollama, vLLM, llama.cpp, SGLang, Cloud) |
| Agents | Agent ABC and implementations (Simple, Orchestrator, OpenClaw, Custom) |
| Memory | Memory backend ABC and implementations (SQLite, FAISS, ColBERT, BM25, Hybrid) |
| Tools | Tool ABC, executor, and built-in tools (Calculator, Think, Retrieval, LLM, FileRead) |
| Intelligence | Heuristic router and model catalog |
| Learning | Router policies, reward functions, and trace-driven learning |
| Traces | Trace storage, collection, and analysis |
| Telemetry | Telemetry storage, aggregation, and instrumented wrappers |
| Benchmarks | Benchmark ABC, suite runner, latency and throughput benchmarks |
| Evals | Evaluation framework: backends, dataset providers, scorers, and suite runner |
| Server | FastAPI application, OpenAI-compatible routes, and Pydantic models |