MCP servers and skills: search, filter by where they run, and compare.
Radix trie-based prompt prefix cache optimizer matching longest common prompt token prefixes to eliminate redundant prefill computation and reduce TTFT.
SkillMIT★ 7No key
Radix trie-based prompt prefix cache optimizer matching longest common prompt token prefixes to eliminate redundant prefill computation and reduce TTFT.
SkillMIT★ 7No key
High-performance OpenAI and Anthropic compatible LLM inference server for Apple Silicon. Native MLX, continuous batching, multimodal models, MCP tool calling, and Claude Code support.
PythonApache-2.0★ 1.6kNo key
Draft-target model speculative decoding verification engine with rejection sampling, acceptance rate telemetry, and dynamic speedup ratio estimation.
SkillMIT★ 8No key
Draft-target model speculative decoding verification engine with rejection sampling, acceptance rate telemetry, and dynamic speedup ratio estimation.
SkillMIT★ 8No key
Virtual paged attention KV-cache memory manager with logical block mapping, non-contiguous physical page allocation, and zero-copy fragmentation tracking.
SkillMIT★ 7No key
Virtual paged attention KV-cache memory manager with logical block mapping, non-contiguous physical page allocation, and zero-copy fragmentation tracking.
SkillMIT★ 7No key
High-precision edge and on-device LLM inference profiler calculating TTFT, TPOT, tokens/second throughput, and percentile jitter distributions (P50/P90/P99).
SkillMIT★ 7No key
High-precision edge and on-device LLM inference profiler calculating TTFT, TPOT, tokens/second throughput, and percentile jitter distributions (P50/P90/P99).
SkillMIT★ 7No key
Symmetric INT8 per-tensor and per-channel quantization engine for LLM weights and activations, with SNR and MSE reconstruction telemetry.
SkillMIT★ 7No key
Symmetric INT8 per-tensor and per-channel quantization engine for LLM weights and activations, with SNR and MSE reconstruction telemetry.
SkillMIT★ 7No key
Radix tree KV cache prefix caching manager for fast decoding (SGLang style)
SkillLink only★ 8
Run DiffDock molecular docking via NVIDIA NIM to predict small-molecule binding poses against protein targets. Use for DiffDock, molecular docking, ligand docking, blind docking, SMILES or SDF ligands
OfficialSkillApache-2.0 AND CC-BY-4.0★ 3.6k in collectionNo key
Measure token savings per AI coding agent, optimize context, and share a live local knowledge graph across 16 CLI clients.
Node.jsMIT★ 560No key
Lossless-by-default context compression for LLM coding agents — proxy, library, CLI, and MCP server. Local-first, cache-correct, reversible.
SkillMIT★ 5No key
Measure what context compression actually costs an LLM agent: where a session's tokens go, and whether a rewrite pays for the prompt cache it invalidates. Rust crate, MCP server and benchmark harness.
Node.jsMIT★ 1Few starsNo key
Production-grade, token-optimized FastMCP SQLite Server with sub-millisecond O(1) schema discovery, opcode execution watchdog, and fuzzy self-healing.
PythonMIT★ 3Few starsNo key
A local-first MCP server that answers, from real data on your machine: How many tokens have I used, from which client, model and session — and what did it cost?
Node.jsMIT★ 1Few starsNo key
Production-Grade Context Engineering Engine, MCP Server & Evidence-First Evaluation Harness for Frontier LLMs
PythonMITFew starsNo key
Inference-aware L4/L7 load balancer for LLM serving fleets, forked from loxilb
GoApache-2.0★ 7No key
MCP server for SAP Commerce Cloud (Hybris): FlexibleSearch, ImpEx, Groovy, cron jobs, catalog sync and OCC product/order access for AI assistants
Node.jsMIT★ 16No key
See where your Claude Code tokens go — cost per call scales 4.3x with context size. Hooks + SQLite + dashboard + MCP server for context window forensics.
PythonMIT★ 19No key
Open-source multi-provider AI backend with automatic 14-engine failover. 36 engines across 7 providers. OpenAI-compatible proxy. Zero-cost frontier AI. Built by Sarma Linux.
SkillMIT★ 7No key
Chat between the AI agents on your machine — they coordinate, ask each other questions, and get notified. No server to run.
SkillApache-2.0★ 5No key
Who stands behind it
