ChainMemory
Tempreon
TheSecondBrain.dev
Memori
Agentmemory
OpenMemory MCP
Pinecone
Memo.ai
RepDB
ChainMemory gives your AI agents persistent memory that belongs to YOU โ not to a single vendor.
Save a memory in ChatGPT, recall it in Claude or Gemini. Available via Chrome extension, MCP server (npm), or REST API. Every memory gets a cryptographic fingerprint and project states are anchored with Merkle proofs, so anyone can independently verify integrity โ no trust required.
Memories consolidate into a structured Project Brain (decisions, milestones, risks) instead of a pile of raw notes. Multi-agent native: Claude, Cursor and GPT share one consolidated state. Free tier available.
RepDB is a one-time-purchase exercise dataset for developers building fitness and workout apps โ not a subscription, not a rate-limited API. You download the data once and own it: JSON (and SQLite on the higher tier), WebP images, and full EN/DE/ES translations, with no per-request billing and no dependency on our servers staying up.
A free tier includes 400 exercises with flat-style 512ร512 images, attribution-licensed for commercial in-app use. The Starter tier ($199) adds the full catalog in classic white-background style. Standard ($399) adds transparent 1024px images, looping animations, exercise relations (similar/progressions/regressions), workout templates, and embeddings โ exclusive to that tier.
Every exercise includes muscle-group highlighting, equipment/muscle icons, MET values, and safety/goal tags. Compared to GIF- or JPG-based competitor APIs, RepDB images are transparent WebP with no watermarks, so they drop into any app UI without a white box around them.
ChainMemory RepDBRepDB's answer:
RepDB is sold as a one-time download, not a metered API โ you own the JSON/SQLite data and WebP images outright, with no rate limits, no per-request billing, and no risk of the vendor cutting off access. It's also the only dataset in this space with EN/DE/ES translations, transparent (alpha-channel) images with no watermark, muscle-group highlighting, safety/goal tags, and looping animations on the higher tier.
RepDB's answer:
RepDB grew out of a consumer workout app its creator was building solo. Sourcing exercise images and data meant either paying for a subscription API with usage caps and no caching rights, or producing everything from scratch. The illustrated, multi-language dataset was built for us first, then split out as its own product once it became clear other indie developers had the same problem and preferred to buy the data outright rather than rent it through an API.
RepDB's answer:
Most alternatives are subscription APIs โ you pay monthly, you're capped on requests, and ExerciseDB's terms of use explicitly forbid caching or storing the data at all, so every image render is a live paid API call. RepDB is the opposite: pay once, download the files, self-host with zero ongoing dependency. It's also the only option offering true DE/ES localization and transparent images instead of a white box behind every exercise.
RepDB's answer:
Solo developers and small teams building fitness or workout-tracking apps (iOS, Android, web) who need licensed exercise images and structured exercise data, but don't want to build their own media pipeline or depend on a rate-limited third-party API.
Tempreon - A personal memory layer for your AI tools, connected over MCP.
TheSecondBrain.dev - One Brain. Everywhere you work. One memory for Claude, ChatGPT, Cursor and every AI tool you use. Runs in your own Cloudflare account. Open source.
Memori - Persistent memory from agent trace, not just conversation
Agentmemory - Persistent memory for Claude Code, Codex & coding agents
OpenMemory MCP - Your private, local memory layer for all AI tools
Pinecone - Search through billions of items for similar matches to any object, in milliseconds. Itโs the next generation of search, an API call away.