No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by yantrikos · MCP Server · ★ 62
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is yantrikdb safe to install? View the security audit →
YantrikDB — A Cognitive Memory Engine for Persistent AI Systems The memory engine for AI that actually knows you. Get Started in 60 Seconds For AI agents (MCP — works with Claude, Cursor, Windsurf, Copilot) Add to your MCP client config: That's it. The agent auto-recalls context, auto-remembers decisions, and auto-detects contradictions — no prompting needed. See yantrikdb-mcp for full docs. As a Python library The engine ships a default embedder (, 7 MB, distilled from BGE-base-en-v1.5) — / work out of the box. No install. No first-run model download. No ONNX runtime. Just one . python import yantrikdb Default: bundled embedder, dim=64. Just works. db = yantrikdb.YantrikDB.withdefault("memory.db") db.record("Alice is the engineering lead", importance=0.8, domain="people") db.record("Project deadline is March 30", importance=0.9, domain="work") db.record("User prefers dark mode", i
| Stars | 62 |
| Forks | 19 |
| Language | Rust |
| Category | MCP Server |
| License | Apache-2.0 |
| Quality Score | 61.9533528700089/100 |
| Open Issues | 31 |
| Last Updated | 2026-09-19 |
| Created | 2026-02-23 |
| Platforms | claude-code, mcp, rust |
| Est. Tokens | ~27k |
Looking for a yantrikdb alternative? If you're comparing yantrikdb with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
🧠 The Brain for Your AI — Local-first memory engine for AI agents. Store, recall, and search memories with se
Open-source local-first cognitive memory. AGM-compliant belief revision (49/49 postulates). When a fact change
A local dual-layer memory pattern for AI agents: a compact, human-readable markdown index paired with semantic
Local memory infrastructure for AI agents. Store knowledge and skills in isolated vaults you compose, control
Local, LLM-free memory for AI agents. A single offline Rust binary — deterministic and auditable — that learns
Agentic AI memory with Ebbinghaus forgetting curve decay. +16pp better recall than Mem0 on LoCoMo.
Explore other popular mcp server tools:
yantrikdb is Cognitive memory engine for AI agents — temporal decay, contradiction detection, autonomous consolidation, knowledge graph, ANN recall via HNSW. Embeddable Rust library with Python bindings; powers ya. It is categorized as a MCP Server with 62 GitHub stars.
yantrikdb is primarily written in Rust. It covers topics such as agent-memory, ai-agents, anthropic.
You can find installation instructions and usage details in the yantrikdb GitHub repository at github.com/yantrikos/yantrikdb. The project has 62 stars and 19 forks, indicating an active community.
yantrikdb is released under the Apache-2.0 license, making it free to use and modify according to the license terms.
The top alternatives to yantrikdb on Agent Skills Hub include uteke, atlas, zer0dex. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: