Full-weight Qwen decision model with calibrated probabilities, training code, REST API, and playground.
☆134Sep 22, 2026Updated last month
Alternatives and similar repositories for autojev
Users that are interested in autojev are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- JEV-inspired parallel decisions for CUDA LLMs. One context, many decisions. vLLM API, game-agent examples, and reproducible benchmarks.☆76Sep 18, 2026Updated last month
- Millisecond decisions, any domain: a 0.8B open "System 1" model that picks between your options with calibrated probabilities. One base, …☆1,582Updated this week
- ☆14Jan 13, 2026Updated 9 months ago
- Typed JSON inference with DiffusionGemma, with Every and Jev benchmark results☆43Sep 16, 2026Updated last month
- RL a search agent on SEC filings with Tinker (Dr. GRPO, gpt-oss-20b)☆24Sep 17, 2026Updated last month
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- Real browser automation with local GLiNER2 inference and open weights. Work in progress. Contributions welcome.☆81Oct 22, 2026Updated 2 weeks ago
- A self-hosted drop-in replacement for TypeSafe's jev, powered by GliFormer.☆312Sep 20, 2026Updated last month
- Faster inference backend for Open-Jev-27B: fused CUDA kernels, prefix tree, CUDA Graphs (B300, bf16)☆90Sep 28, 2026Updated last month
- Jev-compatible API endpoint based on open models (prefill-only)☆334Oct 1, 2026Updated last month
- 🍡 30x faster tokenization for every HuggingFace model☆56Updated this week
- A family of System One-style models fine-tuned from Qwen3.5, designed for one-pass typed decisions with calibrated probabilities.☆1,079Oct 20, 2026Updated 2 weeks ago
- Trace mining for post-training. Filter trajectories, draft verifiers, export SFT and RL data.☆137Updated this week
- ☆21Apr 13, 2026Updated 6 months ago
- Let an LLM write its own tools at runtime: parsed with acorn, versioned in SQLite, run in a supervised worker process☆22Sep 11, 2026Updated last month
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- Local typed decisions, contrastive data curation, and model evaluation.☆2,287Oct 24, 2026Updated 2 weeks ago
- ☆22Mar 23, 2026Updated 7 months ago
- Let your AI agents use your real browser: an MCP server and a Chromium extension☆32Updated this week
- A minimal implementation of agent skills - a lightweight, open format for extending AI agents with specialized capabilities.☆11Dec 23, 2025Updated 10 months ago
- Use Jev (TypeSafe's System One model) as a calibrated reranker: one call, up to 30 documents, a probability per document. Apache-2.0.☆19Sep 17, 2026Updated last month
- ☆18Jun 23, 2026Updated 4 months ago
- A miniature end-to-end reproduction of the Composer 2 training pipeline on a single NVIDIA GH200 480GB, using GLM-4-9B as the base model.☆15Oct 27, 2026Updated last week
- This repository helps you evaluate your models on the FreshStack benchmark!☆33Updated this week
- Highly concurrent and fast content processing for Mighty Inference Server☆10Feb 6, 2023Updated 3 years ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- Official repository for the paper "DR-DCI: Scaling Direct Corpus Interaction via Dynamic Workspace Expansion"☆22Aug 2, 2026Updated 3 months ago
- JevK5: open-weight alternative to TypeSafe Jev. Typed decisions with probabilities in one forward pass; Apache-2.0 weights and code.☆160Sep 28, 2026Updated last month
- A Postgres-optimized fork of Tantivy, the Lucene-inspired search engine library☆11Updated this week
- TransMix: Transformer-based Value Function Decomposition for Cooperative Multi-agent Reinforcement Learning☆11Oct 18, 2022Updated 4 years ago
- The best ChatGPT that $100 can buy.☆61Oct 27, 2026Updated last week
- ☆14Mar 29, 2025Updated last year
- ☆32Oct 27, 2026Updated last week
- ☆15Apr 16, 2026Updated 6 months ago
- ☆68May 26, 2026Updated 5 months ago
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- FineEnvs — RL Environments 101: building and scaling RL environments in the age of LLMs☆547Updated this week
- ☆11Aug 9, 2022Updated 4 years ago
- Turn any open model into a classifier/jev endpoint☆646Oct 7, 2026Updated 3 weeks ago
- Documentation linting☆22Oct 22, 2024Updated 2 years ago
- PorTAL generates portable task specific LoRA adapters that can efficiently transfer across language models.☆129Jul 27, 2026Updated 3 months ago
- Code, (text) data, data statement + annotation guidelines for Betthupferl (“A multi-dialectal dataset for German dialect ASR and dialect-…☆10Oct 2, 2025Updated last year
- A parallel native tool caling deep search agentic framework with base window retention observation masking context management.☆25Sep 22, 2026Updated last month