Thanks to visit codestin.com
Credit goes to www.betterdb.com

Give your AI agents long-term memory, self-tuning caching, and retrieval in one SDK.

Runs on any Valkey or Redis you own. Observable at every layer, no lock-in.

Drop-in adapters for the stack you already use

OpenAIOpenAI Agents SDKAnthropicLangChainLangGraphLlamaIndexVercel AI SDK

The cache tunes itself

No other Valkey or Redis cache library does this.

Agent(via MCP)Reads hit rate, similaritydistribution, tool effectivenessProposal queue Threshold, TTL adjust,or targeted invalidationHuman approves Reviews reasoning inBetterDB MonitorValkey HSET {name}:__configthreshold, tool policiesCache library Polls config, applieswithin seconds, no restartobserves new behavior
See the full closed-loop example

Measured, not asserted

~93%

Recall at scale

holds from the small split (~98%) to LongMemEval-M — a ~10× larger haystack, 500 questions, ~475 sessions each — with hybrid rerank
0.7ms

p50 cache lookup

semantic-cache hit latency, roughly 100× faster than a hosted cache
Anywhere

deploy on any Valkey

run it on a Valkey you already operate, or let us provision a managed one — open core, built on open-source Valkey, no lock-in
See the benchmarks

How BetterDB memory compares

Capability@betterdb/agent-memoryMem0ZepRedis Iris
Runs on Valkey and Redis you operatePluggable backendsGraph DBRedis Enterprise / Cloud
Open core, self-host with a real exitMIT coreApache 2.0; graph gated to ProGraphiti OSS; CE deprecatedProprietary
Bundled semantic LLM cacheExact + semantic, multi-tierNoneNoneLangCache, separate
See the full comparison

Self-hosting the open source version?

BetterDB's core is open source under MIT License. Install it from your ecosystem of choice, or start on managed BetterDB Cloud.

Build your context layer on Valkey

Memory, caching, and retrieval for your agents, on infrastructure you control. Self-host on any Valkey or Redis, or let us run it managed - own your data, no lock-in.

Codestin Search App