47,133 repositories indexed
25–48 of 187 · Most stars
Serve large Qwen models fast on the GPUs you actually own. Qwen3.8-27B on a single 24 GB card with vLLM: 127 tok/s single-user (381 when the answer quotes the prompt), ~1,035 tok/s at 64 concurrent, 150k-262k context. vLLM patches, requant pipeline, benchmarks.
Project Maya - run GLM-5.3-Flash (321B MoE), DeepSeek-V4.1-Flash-1017 (748B MoE) and MiniMax-M3.1-Flash (428B MoE) privately on your own GPU(s), from one card to 16, NVIDIA or AMD, Linux or Windows. Engine, server, dashboard, OpenAI- and Anthropic-compatible API, quant tools.
🎬 Evidence-led Seedance 2.5 / 2.0 prompt library: 840+ cases traced to original posts, 490+ cross-model retest runs, 27 copy-ready templates, 79 installable AI-video Skills. Synced daily from goodcase.ai. EN / 中文 / 日本語.
TranslatedTencent CodeBuddy account pool management console with a built-in OpenAI-compatible reverse proxy gateway: bulk onboarding of accounts via QR code scan, scheduled check-ins and keep-alive, key grouping and distribution, IP and model whitelists, call logs and usage statistics; supports one-click updates with signature verification.
A curated, battle-tested AI-coding toolkit: Claude Code plugins, subagent orchestration, quality gates, and ready-to-copy prompts, extracted from real production use.
🛡️ BLA (Blind LLM Agents) — Adversarial defense shield that protects binaries, Electron apps, JS bundles, Python, and WebAssembly against AI reverse-engineering agents like REA. Poison -> Exhaust -> Hallucinate.
A local inference engine for Apple silicon, built around the model.
Connect your company's data, let an agent draft an ontology over it, and load it into HelixDB as one graph you can explore and ask questions of. Hosted at foundry.helix-db.com, or run it on your own machine.
Steering-first neuron explorer for Qwen3.5-4B: push every MLP neuron, keep every rollout, browse the results
TranslatedLocal AI routing gateway with Agent client takeover — reuse existing client logins, call 50+ AI clients through one base URL, with unified OpenAI / Anthropic / Images APIs, multi-account routing, check-in, balance and request reports
On device Firewall for Coding and Personal Agents
UNIGIT public brand and ecosystem hub — AI should work for everyone.
Translatedvm2api: converts subscriptions into an API using a fully realistic virtual machine emulation approach
Open decision models from 0.8B to 27B: a calibrated probability for every option in one pass, and a short thought only when unsure. Engine for vLLM, llama.cpp and MLX.
1M param OCR model - runs on CPU, 15x faster than tesseract, close to 1B+ param models in accuracy
Turn any LLM into a Jev-style decision model: typed decisions, real probabilities, no training. (continue updating, welcome any issue and PR request)
Model fingerprint detection with a shared Web and Bun CLI reference bank
TranslatedAn Agent tavern based on DSH. A tavern-style text game Agent. Compatible with the SillyTavern ecosystem; character cards can be imported directly and played. Faster, more stable, more lively. Works with all models. Can also be played on mobile phones.
A free AI assistant and survival library that runs on your own computer, with no internet needed. Shows the source of every answer.
A Go-based OpenCode Zen / Zen Go API proxy with OpenAI & Anthropic API compatibility, key/proxy pooling, automatic routing, and WebUI.
🛡️ Free open-source AI-powered security terminal & vulnerability scanner (CVE, SBOM). Supports SSH, SFTP, RDP, VNC, Serial, and 12+ autonomous AI agents (DeepSeek, OpenAI) for automated security workflows, CTF & DevSecOps. Cross-platform & Web UI.
Trace-native CI/CD for AI agents: grade production traces, cluster failures, freeze them into replayable regression tests, and block PRs that regress. Self-hostable.
The repository host gives no description.
GVS5H: Five Qwen3.8-27B Models Match Claude Fable 5 on LiveCodeBench Hard | Fable 5 Level Coding for a Fifth the Price - or on a Single GPU