Wax
Shared Single-file memory layer for all your agents, sub mili-second RAG over text, photo and video on Apple Silicon.. No Server. No API. One File. Pure Swift - christopherkarani/Wax
Wax at a Glance
- Pricing
- Free
- How you use it
- MCP server, CLI, or Swift SDK
- Who it's for
- AI agents and developers building on-device models
- Works with
- Claude Code Codex Cursor Hermes OpenClaw Apple Foundation Models
Wax Key Features
- hybrid text-vector search
- local file storage
- multimodal RAG
- shared agent memory
Can't Find What You're Looking For?
We build custom AI agents tailored to your specific business needs. From ideation to deployment, TinyAI.Tools is your partner in AI innovation.
No commitment required. Let's discuss your ideas.
Wax Alternatives
Swarm
Type-safe tools, on-device inference, multi-agent workflows, memory, and guardrails, in one Swift-native runtime - christopherkarani/Swarm
basemind
The context and communication layer for coding agents. A pure-Rust code map, document RAG, git intelligence, shared memory, and agent-to-agent comms — served over MCP.
ClawMem
On-device memory layer for AI agents. Claude Code, OpenClaw and Hermes. Hooks + MCP server + hybrid RAG search. - yoloshii/ClawMem
agent-device
Open source device layer for coding agents: control mobile, web, TV and desktop apps on devices and simulators, local or in the cloud, via CLI, MCP or Node.js.
Agent Smith
A safety-focused multi-agent workforce for your Mac: an orchestrator, workers with a real shell, a security agent that reviews every tool call, and independent acceptance validation. Native Swift/SwiftUI, bring your own model. - drewster99/macos-agen
moss
Moss delivers sub-10ms semantic search for conversational AI, voice agents, and copilots. Connect your data once — Moss indexes and distributes it wherever your agent runs: in-browser, on-device, or in the cloud.