[upstream-sync] README.md from ARUNAGIRINATHAN-K/awesome-ai-agents-2026@75df871e [catalogue]

Reviewed-on: #23

upstream/ARUNAGIRINATHAN-K-awesome-ai-agents-2026/catalogue/README.md

@@ -2,9 +2,9 @@
 title: "Awesome AI Agents 2026"
 task: ""
 lineage_type: import
-upstream_source: https://github.com/ARUNAGIRINATHAN-K/awesome-ai-agents-2026/blob/91ecee02/README.md
-upstream_sha: 91ecee02
-imported_at: 2026-07-13
+upstream_source: https://github.com/ARUNAGIRINATHAN-K/awesome-ai-agents-2026/blob/75df871e/README.md
+upstream_sha: 75df871e
+imported_at: 2026-07-16
 prompt_class: catalogue
 upstream_changes: accepted
 author: upstream
@@ -139,6 +139,7 @@ validated: false
 - [Chroma](https://github.com/chroma-core/chroma) `🌱` `[Python]` `[Vector DB]` - Lightweight, embeddable vector store for building memory-augmented AI agents with fast semantic retrieval.
 - [cognee](https://github.com/topoteretes/cognee) `🌱` `[Python]` `[Graph-Based]` - Knowledge engine for AI agent memory, set up in 6 lines of code with graph-based knowledge extraction.
 - [Cortex Memory](https://github.com/prem-research/cortex) `🌱` `[Python]` `[Vector DB]` - Full-stack solution for agent memory covering extraction, vector search, and optimization.
+- [Engrava](https://github.com/sovantica/engrava) `🔬` `[Python]` `[Graph-Based]` - Stores agent memory as a typed knowledge graph with hybrid search and a tamper-evident journal, embedded in SQLite.
 - [graphiti](https://github.com/getzep/graphiti) `🌱` `[Python]` `[Multi-Agent]` - Build real-time knowledge graphs for AI agents with automatic entity extraction and linking.
 - [Kage](https://github.com/kage-core/Kage) `🌱` `[TypeScript]` `[MCP]` - Git-native memory for coding agents that stores decisions and fixes as repo files and verifies them against the codebase, withholding stale knowledge.
 - [LanceDB](https://github.com/lancedb/lancedb) `🌱` `[Rust]` `[Vector DB]` - Serverless vector search database embedded directly in the agent process with no infrastructure needed.
@@ -230,6 +231,7 @@ Sandboxes, web scrapers, browser automation, and networking layers that agents d
 - [Agent Bounties](https://github.com/NSPG13/agent-bounties) `🔬` `[Rust]` `[MCP]` - Coordinates verifiable digital bounty workflows designed for agents to post, fund, claim, solve, verify, and earn.
 - [AgentDock](https://github.com/agentdock/agentdock) `🚀` `[Python]` `[Docker]` - Framework for building and deploying production-ready AI agents with composable node architecture.
 - [Agent Starter](https://github.com/raintree-technology/agent-starter) `🌱` `[TypeScript]` `[MCP]` - Project-local config manager that syncs one `agent.json` manifest into Claude Code, Codex, Cursor, and MCP setup while preserving manual edits and detecting drift.
+- [AgentServices](https://agentservices.to) `🚀` `[Python]` `[x402]` - Paid data APIs for AI agents with 54 services, 37 MCP tools, and x402 nanopayments on Base. Market data, onchain analytics, AI inference, and research.
 - [codex-profiles](https://github.com/Ducksss/codex-profiles) `🚀` `[Python]` `[OpenAI]` - Bash CLI for switching OpenAI Codex CLI and Desktop profiles with isolated CODEX_HOME directories.
 - [Crawl4AI](https://github.com/unclecode/crawl4ai) `🌱` `[Python]` `[Multi-Agent]` - Extracts structured data from web pages using LLM-friendly output formats optimized for agent ingestion.
 - [Docling](https://github.com/docling-project/docling) `🌱` `[Python]` `[IDE]` - Parses PDFs, DOCX, and slides into structured text with deep layout understanding for document agents.
@@ -304,6 +306,7 @@ Sandboxes, web scrapers, browser automation, and networking layers that agents d
 - [OWASP Top 10 for Agentic Apps](https://owasp.org/www-project-top-10-for-large-language-model-applications/) `🌱` `[Python]` `[Security]` - Security framework covering goal hijacking, tool misuse, and cascading failure mitigations for agents.
 - [Pluribus](https://github.com/caioribeiroclw-pixel/pluribus) `🔬` `[TypeScript]` `[Observability]` - Generates cross-tool agent context and privacy-safe evidence receipts for loaded authority, handoffs, and skill use.
 - [Rebuff](https://github.com/protectai/rebuff) `🌱` `[Python]` `[Security]` - Self-hardening prompt injection detection system for securing agent inputs against adversarial attacks.
+- [Shipmoor](https://shipmoor.dev) `🔬` `[Python]` `[Testing]` - Local, deterministic verification layer for AI agent code: scans, test evidence, and a binding merge verdict without uploading source.
 - [ai-evaluation](https://github.com/future-agi/ai-evaluation) `🌱` `[Python]` `[Evaluation]` - LLM evaluation framework with 50+ metrics, LLM-as-Judge, and guardrail scanners (jailbreak, PII, injection).
 - [Future AGI](https://github.com/future-agi/future-agi) `🌱` `[Python]` `[Self-Hosted]` - Self-hostable end-to-end agent engineering platform with tracing, evals, guardrails, and gateway.
 
@@ -641,6 +644,7 @@ Platforms that generate full-stack applications, components, or web apps from na
 - [PlayCode Agent](https://playcode.io) `🌱` `[Cloud]` `[Multi-Agent]` - Browser-only lightweight web app creation tool with AI-assisted code generation.
 - [Replit Agent](https://replit.com/agent4) `🌱` `[Cloud]` `[Multi-Agent]` - Builds and deploys full-stack projects from prompts with integrated hosting and collaboration.
 - [v0 by Vercel](https://v0.app) `🚀` `[Cloud]` `[CLI]` - Generates React and Tailwind UI components from text descriptions with one-click Vercel deployment.
+- [VibeKit.bot](https://vibekit.bot) `🔬` `[Cloud]` `[Stateful]` - Builds and hosts full-stack apps from phone chat, with a persistent per-app agent and BYOK keys.
 
 ## Multi-Agent Consumer Platforms
 
@@ -749,6 +753,7 @@ Key data points on the AI agent market covering adoption, growth, valuations, an
 
 Tools for running LLMs locally and self-hosting AI agent platforms with full privacy and control.
 
+- [Avelina](https://avelina.ai) `🌱` `[TypeScript]` `[Telegram]` - Self-hosted personal AI assistant on your own VPS that lives in Telegram, with persistent long-term memory, voice, and Claude-powered reasoning.
 - [GPT4All](https://github.com/nomic-ai/gpt4all) `🌱` `[C++]` `[Local]` - Open-source local chat application that runs LLMs on consumer hardware without cloud dependencies.
 - [Jan](https://github.com/janhq/jan) `🌱` `[TypeScript]` `[Local]` - Open-source ChatGPT alternative that runs 100% offline with local model management and privacy guarantees.
 - [Llamafile](https://github.com/mozilla-ai/llamafile) `🌱` `[C++]` `[Local]` - Distributes LLMs as single executable files with zero setup required from Mozilla.