MCP servers and skills: search, filter by where they run, and compare.
Nothing matches every word exactly, so these are the closest matches.
MCPHub is an embeddable Model Context Protocol (MCP) solution for AI services. Seamlessly integrate MCP servers with OpenAI Agents, LangChain, and Autogen frameworks through a unified interface. Simpl
MCPLink only★ 84
MnemoCore v2.0.0-beta Latest
MCPLink only★ 2Few stars
Personal inbox cognitive triage engine classifying actionability, effort duration, and urgency to prevent attention fragmentation.
SkillLink only★ 7
Personal inbox cognitive triage engine classifying actionability, effort duration, and urgency to prevent attention fragmentation.
SkillLink only★ 7
Compression with a quality contract — cache-aware, causally-pruned LLM context compression for agentic runtimes, certified non-inferior across 7 domains. Works with any SDK.
MCPLink only★ 20
Comprehensive MCP server exposing dozens of capabilities to AI agents: multi-provider LLM delegation, browser automation, document processing, vector ops, and cognitive memory systems
MCPLink only★ 162
Cognitive memory system for AI agents. Separate stores for semantic, episodic, and procedural memory. Multimodal embeddings via Gemini Embedding 2. Grounded in DeepMind AGI cognitive framework.
MCPLink only★ 5
PHI // DRIFT cognitive system for state-aware agents, memory, and evidence-first reasoning.
MCPLink only★ 3Few stars
Autonomous AI Engineer & Sovereign Local Agent. Air-gapped privacy, Orythix cognitive cortex, automated Sentry bug healing, and Neural Forge prompt baking. Runs 100% locally on LM Studio & Ollama + Cl
MCPLink only★ 2Few stars
Read-only mirror of c4reqber (primary repo on GitLab). Cognitive exoskeleton for AI agents and humans: discovery pipeline, formal verification, 21 MCP tools, terminal-first UX. pip install c4reqber. I
MCPLink only★ 1Few stars
Cross-session memory for autonomous ComfyUI workflows. Wires Comfy-Cozy outcomes into the Moneta cognitive substrate.
MCPLink only★ 1Few stars
MCP server for tulbase — local-first context compression for LLM agents. Open-source core, MIT licensed. Pairs with the Compresh paid tier (compre.sh) for Q-protective ranking.
MCPLink only★ 1Few stars
Your Smithers (butler) for MCP token efficiency. Compression proxy that saves tokens on tool results, tool schemas, and server instructions — sits between any AI coding tool (Claude Code, Cursor, Code
MCPLink only★ 1Few stars
Python-first spectral engine for profile-table analysis, modal compression, inverse reconstruction, and MCP/CLI/API workflows.
MCPLink only★ 4Few stars
Memory system for AI agents with hybrid retrieval, MCP tooling, and LongMemEval-leading performance.
MCPLink only★ 3Few stars
MCP server for 1C/BSL code analysis: project-wide diagnostics + per-method cyclomatic/cognitive complexity with refactor triage. Streamable HTTP, bearer auth, built on onec-hbk-bsl (no Java). RU: MCP-
MCPLink only★ 4Few stars
Sovereign Cognitive Memory, Counterfactual Reflection & Fast-Reflex OS for Frontier AI Agents
MCPLink only★ 1Few stars
MCP server for Compresh — production-grade context compression with Q-protective ranking, epistemic markers, and depth-aware adaptation
MCPLink only★ 3Few stars
Metacognitive AI architecture combining Modern Hopfield Networks with entropy-based confusion detection for insight-like problem solving. Implements energy-based search, adaptive beta scaling, and a C
MCPLink only★ 5
A large model context Token compression tool based on local file persistent memory. It loads historical session data through four-layer hierarchical memory management and relevance filtering, achievin
SkillLink only★ 4Few stars
COGNET conversational AI — self-learning, per-user LoRA adaptation, differentiable memory, MCP tools, autonomous self-play
MCPLink only★ 4Few stars
Who stands behind it
