Core memory palace engine for AgentRecall
No description provided.
Recall Desktop SDK
Type-safe SDK for the Recall.ai meeting bot API, generated from the provider's endpoint references.
Zep: Fast, scalable building blocks for production LLM apps
Zep: Fast, scalable building blocks for production LLM apps
Filesystem-backed memory provider for @cuylabs/agent-core
Core module for next-recall
Framework-agnostic Remnic memory engine — orchestrator, storage, extraction, search, trust zones
Coding agent CLI with read, bash, edit, write tools and session management
Is this specifier a node.js core module?
Shared memory engine for Lore — three-tier storage, distillation, gradient context management
Babel compiler core.
Trustworthy memory and security for AI agents. Recall debugging, review queue, OpenClaw session capture, and memory poisoning defence for Claude Code, Codex, OpenClaw, LangChain, and MCP agents.
lightweight memoization
core-js compat
Standard library
Core functions & classes shared by multiple AWS SDK clients.
Positioning library for floating elements: tooltips, popovers, dropdowns, and more
tldts core primitives (internal module)
Standard library
The `util.is*` functions introduced in Node v0.12.
regexpu’s core functionality (i.e. `rewritePattern(pattern, flag)`), capable of translating ES6 Unicode regular expressions to ES5.
A high-level API to automate web browsers
Engram gives AI agents durable, long-term memory. It recalls relevant facts about a user and injects them into the prompt, so an agent appears to remember across sessions. Framework-agnostic core with a ports-and-adapters design; first-class Rails and RubyLLM integration. Your memories live in your own database — no external memory service.
pikuri-memory gives a pikuri-core agent durable, long-lived memory: facts about the user and their work that persist across conversations. It wires a +recall+ tool plus an automatic per-turn prefetch onto an agent via +c.add_extension Pikuri::Memory::Extension.new(...)+ inside the +Agent.new+ block — same opt-in shape as +pikuri-tasks+ / +pikuri-vectordb+. Recall is automatic and synchronous (embed + vector search, milliseconds); capture is automatic and asynchronous (an off-the-interaction-path extraction queue), so a turn never blocks on "what should I remember?". Storage is mem0 (https://github.com/mem0ai/mem0) reached over a thin Faraday HTTP client — the append-only +add+ / read-time +search+ model. Only the *user's own words* are fed to extraction (a write-side hygiene rule that structurally drops system/assistant/tool-sourced junk), and recalled context enters the chat as a +:system+ message so it is provenance-tagged and excluded from the next extraction pass. This release ships the Ruby client + extension + tool against a *bring-your-own* mem0 endpoint; a self-managed mem0 sidecar supervisor (the +ChromaServer+-style docker pattern) is a follow-on.
pikuri-vectordb gives a pikuri-core agent a +vectordb_search+ tool over a local document corpus — agentic search, the agent decides when to retrieve. Ships a swappable backend (a pure-Ruby +Backend::InMemory+ for teaching, plus thin +Backend::Qdrant+ / +Backend::Chroma+ HTTP clients for persistence — Qdrant recommended), a chunker, an embedder wrapper over +RubyLLM.embed+, and an optional +Reranker::LlamaServer+ that speaks +/v1/rerank+ against a cross-encoder model. Text extraction goes through +Pikuri::FileType.read_as_text+ in pikuri-core, which handles plain text / Markdown / PDF; HTML extraction is a deferred follow-up. Hosts wire the feature via +c.add_extension Pikuri::VectorDb::Extension.new(...)+ inside the +Agent.new+ block — same opt-in shape as +pikuri-tasks+ / +pikuri-skills+. The bundled +Pikuri::VectorDb::LIBRARIAN+ persona is the privilege-separated sub-agent counterpart for hosts that want recall to flow through a child rather than the parent's context. Three model endpoints in the full setup — chat (via ruby_llm), an embedder (via +RubyLLM.embed+), and an optional reranker (HTTP +/v1/rerank+). A single +llama-server+ in router mode serves all three by default, loading each cached GGUF on demand; see the gem's README for details.
No description provided.
No description provided.