Inference Engines & InfraFreemium
Recalld
The core loop is write once, retrieve precisely: you POST a conversation turn or document, Recalld extracts atomic facts and timestamps…
VerifiedFreemium
View RecalldCategory
RAG Frameworks
RAG frameworks and libraries (LlamaIndex, Haystack).
Inference Engines & InfraFreemium
Jylus
Jylus ingests streaming data, resolves current and historical state, follows relationships between entities, flags contradictions, and…
VerifiedFreemium
View Jylus
Inference Engines & InfraFreemium
AI·rete·RAG
The tool pairs a deterministic rule engine with retrieval-augmented generation, so every decision is grounded in a defined rule set and can…
VerifiedFreemium
View AI·rete·RAG
Inference Engines & InfraFreemium
Contextual
The engine indexes your repository — symbols, commits, PR threads, docs — into a local graph stored in ~/.contextual, then keeps it live…
VerifiedFreemium
View Contextual
Inference Engines & InfraFreemium
Inference Engines & InfraFree
Mwe-MCP
The store lives on your own server as human-readable Markdown files, which means you can open a file, spot a hallucinated fact, and correct…
VerifiedOSS
View Mwe-MCP
Inference Engines & InfraFreemium
Stele
Stele is a shared memory layer that sits between your agents and your codebase. Every agent reads the same knowledge graph — decisions…
VerifiedFreemium
View Stele
Inference Engines & InfraFreemium
Kit For AI
The core workflow is a single API endpoint: drop in a file, URL, YouTube link, or raw text; get back chunked, embedded, searchable Markdown…
VerifiedFreemium
View Kit For AI
Inference Engines & InfraPaid
WeAura AI Agent
Aura pulls your Prometheus metrics, Kubernetes state, runbooks, and Git history into a single retrieval layer, then answers incident…
Verified
View WeAura AI Agent
Inference Engines & InfraFreemium
Engramma Memory
The library combines exact kNN search, Hopfield energy networks, and multi-head attention in a single local install, so agents can…
VerifiedOSSFreemium
View Engramma Memory