Tag
Explore by tags
Provides a local model gateway and control plane for coding agents — route Claude Code, Codex, Grok CLI, ZCode and compatible clients to multiple providers through one stable local endpoint while managing routing, failover, tools, credentials, and observability.
Provides a lightweight Python harness that turns LLMs into working agents with tool-use, skills, persistent memory, permission controls and multi-agent coordination. Ships with a CLI/React TUI, 43+ built-in tools, a plugin/skill system and the ohmo personal-agent for chat gateways. Best for developers prototyping agent workflows and multi-agent experiments.
Provides high-performance CUDA/CUTLASS kernels implementing Kimi Delta Attention (KDA), accelerating KDA prefill on SM90+ (Hopper) GPUs. Integrates as a drop-in backend for flash-linear-attention, supports native variable-length batching, and targets K=V=128; requires CUDA 12.9+/PyTorch 2.4+.
Terminal-native AI coding agent that reads and edits code, runs shell commands, searches files, fetches web pages, and determines next steps from interactive feedback. Delivered as a single-binary TUI with video input, subagents, a plugin marketplace, and IDE (ACP) integration.
Turns terminal-agent CLIs you already run into a local desktop multi-agent harness: each agent runs as a real terminal process, with shared semantic memory, encrypted on-node messaging, a GOD orchestrator for routing/approvals, and a visual office floor for monitoring.
Provides an open-weight native multimodal agent that understands text and images within a 1,048,576-token context window for long-horizon coding, visual reasoning, and tool-driven workflows. Uses a 2.8T-parameter Mixture-of-Experts architecture (KDA + AttnRes) with MXFP4 quantization; best suited for research and large-scale inference setups.
Provides verified, model-attested end-to-end agent coding and debugging trajectories (JSONL). Each whole-session trace was produced by moonshotai/kimi-k3 on the pi/openrouter runtime, passed acceptance tests and independent model screening — useful for SFT, distillation, and analyzing tool-use behavior.
A 124B hybrid-linear Mixture-of-Experts language model optimized for instruction following, long-context reasoning and agentic workflows, activating ~5.1B parameters per token. Key features include a 256K native context (extendable to 1M), alternating KDA/MLA attention layers, and vLLM/SGLang inference support.
Provides a 57,937-row, quality-filtered multi-teacher SFT distillation corpus combining outputs from Qwen3.8-Max, GLM-5.2 and Kimi K3 across math, code, reasoning, tool-use and dialogue. Includes 24 parquet training views (including a pre-tokenized GLM-4.7 view), configurable sampling weights (sft_balanced), and explicit tool-call trajectories for agent training.
An open-weight LLM focused on deep reasoning, native agentic tool use, and repository-scale code understanding — Mixture-of-Experts architecture with an extended context window and permissive licensing.
Open-weight multimodal Mixture-of-Experts LLM with native vision and a 1,048,576-token context window. 2.8T parameters (104B activated), MXFP4 quantization, released for agentic long-horizon coding, knowledge work, and vision-in-the-loop workflows.
Presents a 2.8T-parameter Mixture-of-Experts multimodal model with a 1-million-token context window and 104 billion activated parameters, targeting long-horizon agentic RL, coding, reasoning, and vision. Key innovations include Kimi Delta Attention, Attention Residuals, Stable LatentMoE (16 of 896 experts active per token), ~2.5× scaling efficiency over Kimi K2, and a public weight release.