19 skills found
remete618 / widemem-aiNext-gen AI memory layer with importance scoring, temporal decay, hierarchical memory, and YMYL prioritization
LycheeMem / LycheeMemLightweight Long-Term Memory for LLM Agents.
PDgit12 / knitbrainThe local-first brain for coding agents: project memory + workflow intelligence + lossless ~50% context savings. MCP server + LLM proxy, zero cloud.
huang-sh / pytorch-fsdpAn open-source, model-agnostic AI workbench for scientific discovery.
ncmonx / icemageToken-efficient context engine for AI coding agents. v2.21.0: brain+token trio — session-aware recall delta, contradiction sentinel, adaptive recall depth. 2416 tests, 42 MCP tools, Elastic-2.0.
HaseebKhalid1507 / VelociRAGLightning-fast RAG for AI agents. ONNX-powered, 4-layer fusion, MCP server. No PyTorch.
MemTensor / MemOSSelf-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings
itayinbarr / little-coderA harness optimized to smaller LLMs
loganionian / 0gmemLong-term conversational memory system for AI agents — cell-based architecture with hybrid BM25 + semantic retrieval. 96% accuracy on LoCoMo benchmark.
manascb1344 / together-mcp-serverMCP server enabling high-quality image generation via Together AI's Flux.1 Schnell model.
rudraptpsingh / axonLocal hardware intelligence for AI coding agents. Zero cloud. Zero telemetry.
alsoleg89 / ai-knotDeterministic, self-hosted long-term memory for AI agents: store facts instead of transcripts, recall only what matters.
vllm-project / semantic-routerA programmable Mixture-of-Models router for heterogeneous LLM inference
raullenchai / Rapid-MLXThe fastest local AI engine for Apple Silicon. 4.2x faster than Ollama, 0.08s cached TTFT, 100% tool calling. 17 tool parsers, prompt cache, reasoning separation, cloud routing. Drop-in OpenAI replacement. Works with Claude Code, Cursor, Aider.
kwon416 / real-estimate-AIPython RAG LangChain + 부동산 통계 정보 open API 챗봇 프로젝트
netdata / netdataThe fastest path to AI-powered full stack observability, even for lean teams.
LuiggiVal08 / toon-memoryMCP server giving AI coding agents offline, token-efficient persistent memory — recall decisions, patterns, and bugs across sessions with 68.5% fewer tokens than re-reading context. No LLM, no server; works with 15+ agents.
Dataojitori / nocturne_memoryA lightweight, rollbackable, and visual Long-Term Memory Server for MCP Agents. Say goodbye to Vector RAG and amnesia. Empower your AI with persistent, graph-like structured memory across any model, session, or tool. Drop-in replacement for OpenClaw.
get-vix / vixSleek, Fast and Token Efficient AI Coding Agent
