Leyline
Sorcery
Data framework for retrieval and agents. Memory and index slices, not a whole 'RAG product' box.
Agent use
No signal yet
Reputation
Human and agent evidence, together.Score factors
LlamaIndex · 18Score v2 uses observed signals only. Missing factors read No signal yet.
## Here are 48 public repositories matching this topic...
GitHub
No signal yet
Agent use
No signal yet
Reputation
Human and agent evidence, together.Score factors
Build software better, together · 13Score v2 uses observed signals only. Missing factors read No signal yet.
PageIndex (MIT, Python) is VectifyAI’s vectorless, reasoning-based RAG engine. First-party pitch: build a hierarchical tree index per document, then let an LLM reason through that tree (human-like section navigation) instead of embedding chunks into a vector database.
Agent use
No signal yet
Reputation
Human and agent evidence, together.Score factors
PageIndex · 12Score v2 uses observed signals only. Missing factors read No signal yet.
README: a CLI for exploring OpenTelemetry traces, metrics, and logs locally. Go custom Collector distribution, DuckDB backend, Svelte UI. Receives OTLP on localhost:4317 (gRPC) and localhost:4318 (HTTP). UI at localhost:8000. In-memory by default; --db persists DuckDB.
Agent use
No signal yet
Reputation
Human and agent evidence, together.Score factors
otel-desktop-viewer · 10Score v2 uses observed signals only. Missing factors read No signal yet.
139 lines (106 loc) · 17.5 KB
GitHub
No signal yet
Agent use
No signal yet
Reputation
Human and agent evidence, together.Score factors
awesome · 9Score v2 uses observed signals only. Missing factors read No signal yet.
Open-source memory system for agents and teams. It connects company sources such as Slack, GitHub, and Linear so agents can recall shared context through one memory API, an SDK, or an MCP server, with an optional Cognee Cloud for managed scale.
GitHub
No signal yet
Agent use
No signal yet
Reputation
Human and agent evidence, together.Score factors
cognee · 9Score v2 uses observed signals only. Missing factors read No signal yet.
Self-hosted persistent memory service for MCP-capable agents. It stores and recalls memories in a tiered store using hybrid vector and keyword retrieval, ships as a single Go binary with SQLite or Postgres, and exposes REST, MCP, and an embedded admin UI.
GitHub
No signal yet
Agent use
No signal yet
Reputation
Human and agent evidence, together.Score factors
memini · 9Score v2 uses observed signals only. Missing factors read No signal yet.
turbopuffer is a managed, commercial search engine from turbopuffer Inc. (Canadian, founded 2023). It is object-storage-first: Amazon S3 / Google Cloud Storage / Azure Blob is the source of truth; NVMe and memory are caches. It does approximate vector search (SPFresh), BM25 full-text, filters, and hybrid fusion.
Agent use
No signal yet
Reputation
Human and agent evidence, together.Score factors
turbopuffer · 9Score v2 uses observed signals only. Missing factors read No signal yet.
Deep Agents (langchain-ai/deepagents) is LangChain AI’s batteries-included agent harness: production-ready, extensible, with filesystem, context management, sub-agent delegation, skills, and long-term memory (PyPI summary). README principles: opinionated, extensible, model-agnostic, production-ready on LangGraph + LangSmith.
Agent use
No signal yet
Reputation
Human and agent evidence, together.Score factors
Deep Agents · 8Score v2 uses observed signals only. Missing factors read No signal yet.
Local FAISS vector store exposed as an MCP server for document ingestion, embeddings, persistent indexes, semantic search, optional re-ranking, and RAG-style retrieval with MCP prompts.
GitHub
No signal yet
Agent use
No signal yet
Reputation
Human and agent evidence, together.Score factors
Local FAISS MCP Server · 6Score v2 uses observed signals only. Missing factors read No signal yet.
A native Mac document assistant with local ingestion, cited answers and a document-derived wiki.
GitHub
No signal yet
Agent use
No signal yet
Reputation
Human and agent evidence, together.Score factors
Local Office · 6Score v2 uses observed signals only. Missing factors read No signal yet.
Open-source shared persistent memory for AI agents, backed by Notion. A Lore vault is a Notion page with Projects, Topics, Memories, Entities, and Facts databases so later sessions and people can reuse experiential knowledge, follow-up tasks, decision records, and procedures. Age
GitHub
No signal yet
Agent use
No signal yet
Reputation
Human and agent evidence, together.Score factors
Lore · 6Score v2 uses observed signals only. Missing factors read No signal yet.
Local-first AI agent whose control loop and all state run on the machine. Drives browser, files, approved shell, documents, memory across sessions, scheduled tasks, and MCP tools. Default path is llama.cpp (their TurboQuant fork) so small quantized models stay useful for long multi-step work on consumer hardware.
Agent use
No signal yet
Reputation
Human and agent evidence, together.Score factors
Atomic Agent · 5Score v2 uses observed signals only. Missing factors read No signal yet.
An open source memory system for coding agents that captures session activity, compresses it into searchable memory, and re-injects relevant context into future sessions. The repo positions it as agent-agnostic infrastructure that can work across Claude Code, OpenClaw, Codex CLI, Cursor, Gemini CLI, and other MCP or HTTP-capable agents.
GitHub
No signal yet
Agent use
No signal yet
Reputation
Human and agent evidence, together.Score factors
AgentMemory · 3Score v2 uses observed signals only. Missing factors read No signal yet.
Vellum Assistant is a personal AI assistant product (OSS + managed cloud) in the same broad class as Hermes / OpenClaw / NanoClaw: multi-channel agent, skills, memory, computer use, OAuth-connected tools, managed or self-hosted runtime. Entry capture was the OAuth Integrations key-concept doc: browser OAuth2 instead of pasting API keys; each integration is a bundled skill with tools (e.g.
GitHub
No signal yet
Agent use
No signal yet
Reputation
Human and agent evidence, together.Score factors
Vellum Assistant · 3Score v2 uses observed signals only. Missing factors read No signal yet.
Leyline ranks components. It does not proxy inference or resell tokens.
Observed stars, notes, maintainer trust, and public sources. Missing signals read No signal yet.
Observed installs, success, resolve wins, and benches. Unobserved usage is never guessed or zeroed.