LLM-native optimization solver: LP, MIP, portfolio & scheduling via HiGHS/OR-Tools.
Loading the directory
Loading the directory
MCP servers for embeddings, vector stores, model gateways, and long-term memory.
LLM-native optimization solver: LP, MIP, portfolio & scheduling via HiGHS/OR-Tools.
Adaptive memory for AI agents — FAISS search, chat extraction, cross-project linking
CognOS trust scoring (C=p·(1-Ue-Ua)) and session trace storage as MCP tools.
Temporal memory for AI with decay and reinforcement. Two-layer storage (JSONL + Markdown).
Context Engineering Engine. Provides cognitive tools, memory structures, and agent patterns.
Multi-agent memory intelligence with expertise tracking and conflict detection
Persistent memory for AI agents with rollback, audit trails, and semantic search.
18 tools: agent memory, API drift detection, and HMAC-signed trust receipts
Zero model drift between AI agents. Session continuity for Claude, GPT, Gemini, and any LLM.
31 MCP tools for ESG data extraction, PDF processing, vector search, and EU regulation analysis.
Encrypted mail, shared memory, and persistent context for AI agents.
MCP server for Styx — intelligent AI routing across OpenAI, Anthropic, Google, and Mistral.
Text extraction, keyword extraction, language detection, and chunking for RAG
MCP server that reduces LLM context by removing code comments and converting data formats to TOON
BM25 search + tree navigation over markdown docs for AI agents. No embeddings, no LLM calls.
Memori MCP server — persistent AI memory with recall and augmentation tools
Universal web content extraction — any URL to LLM-ready markdown. HTML, YouTube, PDF, DOCX.
Cloud-persistent, semantic-search memory MCP — drop-in for server-memory, backed by ZeroDB.
MCP server for Ordali memory: SQLite-backed project memory and governance traces.
Zero model drift between AI agents. Session continuity for Claude, GPT, Gemini, and any LLM.
Web scraping for AI agents. Converts URLs to clean, LLM-ready Markdown with anti-bot bypass.
MCP server for Skim code transformation. Compresses code 60-95% for LLM context optimization.
Hands bounded coding work to cheaper worker agents: verified answers, exact diffs, cost receipts.
SQLite-backed MCP server for persistent memory, full-text retrieval, and graph traversal.