🏄 Scalable embedding, reasoning, ranking for images and sentences with CLIP
- bert
- sentence-encoding
- deep-learning
- clip-model
Repository Index
73,862 visible repositories in the index
1–24 of 29 · Most stars
BISHENG is an open-source enterprise Agent platform for building, deploying, and managing AI applications. It combines AI agents, workflows, RAG and knowledge management, desktop agent integration, and vibecoding app hosting with unified model management, evaluation, observability, access control, and enterprise administration.
OpenCompass is an LLM evaluation platform, supporting a wide range of models from OpenAI, Anthropic, Gemini, Qwen, GLM, DeepSeek, etc, across 100+ datasets covering knowledge, reasoning, coding, science, language, long-context, and safety.
- evaluation
- benchmark
- large-language-model
- llm
DeepSpec: a full-stack codebase for training and evaluating speculative decoding algorithms
Agent OS: the agent gets smarter on its own. We just hold the line: Interview-gated, staged evaluation, budgeted evolution loop. MCP server, 14 runtimes: Claude Code, Codex CLI, Gemini CLI, OpenCode, Copilot, Kiro and more.
- ai-agent
- agent-os
- llm-orchestration
- agentic-ai
The CLI and skills that turn any coding assistant into an expert at creating, evaluating, and deploying AI agents on Google Cloud.
- adk
- agent-development-kit
- agents
- coding-agent
Democratizing Reinforcement Learning for LLMs
- agent-framework
- agentic-workflow
- distributed-training
- llm-training
OpenClaw-RL: Train any agent simply by talking
- async
- memory-systems
- open-claw
- openclaw-skills
GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models
Rapid-MLX is an open-source (Apache 2.0) OpenAI- and Anthropic-compatible LLM inference server for Apple Silicon, built on MLX, focused on reliable tool calling for coding agents. Up to 4× faster than Apple's MLX (mlx-lm) on the same weights.
- apple-silicon
- local-llm
- macos
- mlx
LLM-as-a-Verifier is a general-purpose framework that provides fine-grained feedback for any agent without requiring additional training. It achieves SOTA performance across coding, robotics, and medical agentic benchmarks.
Intercept and inspect Coding Agent API traffic from Claude Code, Codex CLI, Gemini CLI, Cursor CLI, OpenCode, Kimi/Kimi Code, Pi, and Hermes in a local trace viewer.
Find the ghost tokens. Fix them. Survive compaction. Avoid context quality decay.
- claude-code
- token-optimization
- context-window
- token-usage
Formal verification for AI: a Lean 4 + Dafny proof checker that catches fake AI proofs (reward hacking), and verified recursive self-improvement (RSI) for coding agents. AI for math, physics and software engineering.
- proof-assistant
- lean4
- ai-agents
- ai-for-math
The fastest way to run Qwen 3.8 Flash Next, Qwen 3.8 27B and Ternary Bonsai 2 27B on a Mac: 125 tok/s in OpenCode on an M5 Max, and a 27B model on 16 GB Macs. Native MTP speculative decoding on Apple Silicon, exact at any temperature. OpenAI and Anthropic compatible local server.
- apple-silicon
- local-ai
- mlx
- mtp
[NeurIPS 2026] Safety failures in coding agents and frontier LLMs. Reproducible workspaces for studying when AI agents generate unsafe data during task completion.
The Fable Workflow: how Claude Fable 5 worked, distilled into skills any model can run, with the eval that keeps it honest. Think / act / prove.
Web Crawling and RAG Capabilities for AI Agents and AI Coding Assistants
AI-native agent harness for coding workflows by python: multi-model LLM orchestration, stateful sessions, tool governance, traceable delivery, and provider routing for GPT, Claude, DeepSeek, Qwen, Kimi, GLM, and MiniMax.
Databricks Toolkit for Coding Agents provided by Field Engineering
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
Run 284B DeepSeek-V4-Flash (<59GiB RAM: 41.1 cold pp, 9.1 N=1 tg, up to 25.3 spec tok/s) & 30B MoEs (22.4 N=1 / 111.6 spec tok/s) on 64GB CPU (0 GPUs).
Turn DeepSeek Harness into a self-hosted enterprise Agent platform with knowledge, deep research, content generation, vibe coding, browser automation, governance, and admin controls.
- agent
- ai-agents
- dsh-plugin
- enterprise-agents
TranslatedQoder international and China multi-account reverse proxy gateway, a multi-account OpenAI-compatible gateway hub for Qoder's international and China dual regions — COSY-signed inference, stable device fingerprints to avoid risk control, OAuth device authorization for client-free login, daily check-in and Pro benefits, background scheduled task scheduler, web monitoring dashboard, supporting Codex / Claude Code and standard OpenAI clients
- aliyun
- api-gateway
- claude-code
- codex