Jev SDKs and developer tools
Find clients, workflow controls, inference runtimes and training tools. Compare their purpose, publisher and documented limits.
20 distinct projects · Last curated · JSON
| Project and source | Purpose | Scope and limits |
|---|---|---|
| TypeSafe Python SDK | API integration | The official sync and async client for typed Jev questions and answers. |
| TypeSafe JavaScript SDK | API integration | The official JavaScript client with answer types inferred from your questions. |
| TypeSafe Agent Skills | API integration | Official guidance for coding agents building with the System One API. |
| TypeSafe Public Examples | API integrationWorkflow control | Source code accompanying official documentation, demos, and cookbooks. |
| protoc-gen-jev | API integration | Generates typed Go, TypeScript and Python clients from annotated Protobuf schemas. Generator and runtime releases must be matched; backend behavior was not tested here. |
| TypeSafe for n8n | Workflow control | TypeSafe-maintained nodes for adding typed decisions to n8n workflows. |
| Abide | Workflow control | Jev checks edits and turns against compiled project rules and requests repairs; missing credentials or network let edits pass unchecked, and replay findings depend on the chosen rubric. |
| jev-fabric | Workflow control | Native process orchestration with bounded logs, deadlines and explicit typed decisions; commands run with caller privileges, exit status needs outcome checks, and selected policy proofs do not verify the whole runtime. |
| atoma | Workflow control | Multi-agent planning, execution and evidence review with Jev routing; shared agent/skill learning can expose document-derived material across organizations, and tenant isolation is not independently audited. |
| JevLang | Workflow control | TypeScript/Python policy layer separates typed model answers from routing and action dispatch, with documented journals and replay; a trace does not establish truthful inputs or calibrated thresholds. |
| cua-s1.js | Inference runtimes | Browser ports of Cua form and next-action models; output-parity checks do not establish generalization, and the small form model can confidently skip unfamiliar fields. |
| jev-omni.js | Inference runtimes | Work-in-progress WebGPU port for Jev-Omni text and image decisions; audio/video are unfinished, model downloads are large, and reported parity is limited to selected fixtures and hardware. |
| mJev | Inference runtimes | Shared-context candidate scoring with HF/vLLM routes; normalized option probabilities are not calibrated confidence, and the reported cache speedup trades higher memory in one controlled video setup. |
| FRIDA-Decisions | Inference runtimes | Packed Russian–English encoder runtime for typed questions and ranking; state truncation, Russian instruction suffixes and margin-versus-probability semantics remain explicit. |
| Quyet runtime | Inference runtimes | Runtime for Quyet decision models with checkpoint-dependent English/Vietnamese coverage; it documents ten-option limits and state truncation, without evaluated adversarial robustness. |
| System One Adapter | Training & evaluation | Compare LLMs through the same question interface, with probability outputs and request diagnostics. |
| circuit | Training & evaluationInference runtimes | LoRA and pointer-head training, evaluation and serving for text, image and audio decisions; publisher tests cover selected task sets and do not establish universal calibration or option-order invariance. |
| SearchJev training pipeline | Training & evaluation | Search-agent decision training with soft-label and Brier losses, reliability weights and per-question-type temperature fitting; the documented pipeline and split controls were not reproduced. |
| OpenThai-SystemOne | Training & evaluationInference runtimes | Thai/English text decision-model training and serving pipeline with a slot readout; the documented recipe does not establish independently validated calibration or interface equivalence. |
| sysone decision-learning library | Training & evaluation | Training, calibration and interpretation tools for several text, image and protein backends; documented compatibility checks and small experiments do not validate every backend or workload. |
No matching tools. Change the search or reset the filters.
SDKs connect to an API; independent-model runtimes and training code serve different roles. Entries preserve reviewed documentation scope, not execution by this project. Evidence labels
Compare independent models and licenses · Guide to reproduction scope