157 tagged knowledge base, measured the same way as everything else here.
Browse within: markdown 20agent-memory 17local-first 13embeddings 11python 11RAG 9documentation 8hybrid-search 8fastapi 7fastmcp 7obsidian 7ai-memory 6docker 6chatgpt 5
synpulse8-opensource/pulse8-ai-cortex-knowledge-vault
MCP server Claude CodeCodexCursor +2
PULSE8.ai Cortex — agent-native knowledge OS built on Markdown files. Runs locally from the pulse8-ai-cortex-knowledge-vault Python package. Needs 2 environment variables to run.
MCP server Claude CodeCodexCursor +2
MCP server "total-recall" as configured in strvmarv/total-recall. Runs ${CLAUDE_PLUGIN_ROOT}/bin/start.js with node.
MCP server Claude CodeCodexCursor +2
Cross-session memory and recall for AI agents — git-synced knowledge base, knowledge graph, confidence scoring, hybrid semantic+TF-IDF search, auto-distillation with secrets scrubbing. Runs locally from the agent-knowledge npm package.
MCP server Claude CodeCodexCursor +2
Shared team memory for AI coding agents — MCP server and CLI for persistent, queryable knowledge across sessions and teammates. Runs locally from the knowit npm package.
MCP server Claude CodeCodexCursor +2
LuxAlgo Library — the encyclopedia of trading & technical analysis for AI agents. Free, keyless. Runs locally from the @luxalgo/mcp npm package.
MCP server Claude CodeCodexCursor +2
MCP server "soroka" as configured in AndyShaman/Soroka. Runs locally from the soroka Python package.
MCP server Claude CodeCodexCursor +2
MCP server "scansci-pdf" as configured in Xinyang-Li666/SciCrucible. Launched with scansci-pdf run.
MCP server Claude CodeCodexCursor +2
MCP server "exomem", hosted remotely at substratesystems.io, as configured in Artexis10/exomem.
MCP server Claude CodeCodexCursor +2
Local knowledge substrate for owned markdown/Obsidian vaults, exposed through MCP, REST, and CLI with multimodal OCR/ASR/CLIP search. Runs locally from the exomem Python package.
MCP server Claude CodeCodexCursor +2
MCP server "blink" as configured in arpitnath/blink-query. Launched with /Users/arpit/.bun/bin/bun /Users/arpit/Desktop/playground2.0/blink-query/dist/in.
MCP server Claude CodeCodexCursor +2
MCP server "unforgit" as configured in MiguelMedeiros/unforgit. Launched with unforgit-mcp.
MCP server Claude CodeCodexCursor +2
One shared memory for every AI you use, in plain Markdown files you own. Runs locally from the callosium npm package. Needs 1 environment variable to run.
MCP server Claude CodeCodexCursor +2
Lets the agent inspect and automate a live Chrome instance through the DevTools protocol: performance traces, network, console. Runs locally from the chrome-devtools-mcp npm package.
MCP server Claude CodeCodexCursor +2
Exam-scored knowledge brains your agent searches over MCP, plus a public list of their gaps. Remote server at mozg.sh.
MCP server Claude CodeCodexCursor +2
Model Context Protocol server for Kibi knowledge base. Runs locally from the kibi-mcp npm package.
MCP server Claude CodeCodexCursor +2
MCP server "postgram" as configured in ivo-toby/postgram. Runs in Docker (ghcr.io/ivo-toby/postgram@sha256:29b61fb302bd52862b8eba43305ee2aa4fc072d5f9188652f1fe6324f49d5391). Needs 6 environment variables to run.
MCP server Claude CodeCodexCursor +2
Unified memory and skill infrastructure for AI agents. Runs locally from the memstem Python package.
MCP server Claude CodeCodexCursor +2
MCP server "fpfreference", hosted remotely at mcp.fpf.sh, as configured in venikman/fpf-memory.
MCP server Claude CodeCodexCursor +2
MCP server "sill-ensoul" as configured in sillogic/sill-ensoul. Runs locally from the sill-ensoul Python package.
MCP server Claude CodeCodexCursor +2
MCP Server for Dify workflow integration. Runs locally from the dify-mcp-server npm package.
MCP server Claude CodeCodexCursor +2
Doco CLI and MCP server — one command to connect your AI agent to your knowledge base. Block-level addressing, optimistic concurrency, 29 MCP tools. Runs locally from the doco-agent-cli npm package.
MCP server Claude CodeCodexCursor +2
Plesk MCP server. Runs locally from the plesk-mcp Python package. Needs 4 environment variables to run.
MCP server Claude CodeCodexCursor +2
MCP server "trilium-mcp" as configured in OVDEN13/trilium-mcp. Runs in Docker (ghcr.io/ovden13/trilium-mcp:0.1.5). Needs 4 environment variables to run.
guimatheus92/social-knowledge-base
MCP server Claude CodeCodexCursor +2
MCP server "video-analyzer" as configured in guimatheus92/social-knowledge-base. Runs C:/Users/guilh/repos/mcp-video-analyzer/dist/index.js with node. Needs 5 environment variables to run.