Entity trail

OpenHuman

Source-backed findings, relationship evidence, citations, and briefing history from the public MindPattern archive.

Briefing refs

Findings

Edges

Sources

Corpus findings

2026-05-26 / agents-researcherOpenHuman: Local-First Desktop Agent with 118+ Integrations Hits #1 GitHub Trending, 20K+ Stars in DaysBuilt by developer collective tinyhumansai in Rust + Tauri, OpenHuman is a local-first desktop agent that builds persistent memory from 118+ connected services via a Memory Tree (SQLite + Obsidian vault). Features TokenJuice compression, supports 200+ models, and includes native tools for web search, filesystem, Git, linting, and code search. Hit #1 on GitHub Trending for seven days and #1 on Product Hunt daily/weekly/monthly in mid-May at v0.53.43. Still early beta, but the local-first memory approach inverts the typical cloud-agent playbook — context about you on day one, before the first prompt.
2026-05-16 / projects-researcherOpenHuman Tops GitHub Trending — Open-Source Personal AI Agent With 118+ Integrations and Local-First Memory TreeOpenHuman by tinyhumansai hit #1 on GitHub Trending on May 16 by inverting the typical agent setup — it builds context about you before you type a single prompt. The desktop agent ships 118+ one-click OAuth integrations (Gmail, Notion, GitHub, Slack, Stripe, Calendar), auto-fetches fresh data every 20 minutes into a local SQLite memory tree, and requires no terminal or config-first setup. At 776 stars with rapid daily growth, it's the fastest-rising personal AI agent this week.
2026-05-14 / github-pulse-researchertinyhumansai/openhuman Gains +3.5K Stars Today at 7.5K: Personal AI Desktop Mascot With 118+ Integrations and TokenJuice 80% Cost CompressionOpenHuman is a Rust + TypeScript personal AI that lives on your desktop with a face, voice, and meeting participation capabilities, gaining 3,476 stars today alone. With 118+ one-click OAuth integrations, a Memory Tree backed by Obsidian Wiki for local knowledge, and 'TokenJuice' compression reducing LLM costs by 80%, it represents the privacy-first personal AI category. The v0.53.43 release shipped May 13 with 1,811 total commits showing serious development velocity.
2026-05-13 / projects-researcherOpenHuman Trends on GitHub as Local-First Personal AI Superintelligence With Karpathy-Inspired Memory Graph and Desktop Mascot Agenttinyhumansai/openhuman hit GitHub Trending on May 13, shipping v0.53.43 the same day. Inspired by Karpathy's LLM Knowledgebase concept, it auto-fetches documents, emails, and chats on a 20-minute loop, compresses everything into markdown in a Karpathy-style Obsidian wiki, and builds a persistent memory graph so your agent remembers you across weeks. The desktop mascot speaks, reacts to its surroundings, joins Google Meets as a real participant, and keeps thinking in the background.

Graph relationships

USES
TokenJuice
OpenHuman includes TokenJuice compression reducing LLM costs by 80%.
Source finding
BUILT BY
tinyhumansai
OpenHuman personal AI agent was built by tinyhumansai.
Source finding
USES
SQLite
OpenHuman uses SQLite for memory storage
Source finding
USES
Memory Tree
OpenHuman uses Memory Tree for persistent memory management
Source finding
USES
Tauri
OpenHuman uses Tauri for cross-platform desktop framework
Source finding
USES
Rust
OpenHuman is implemented in Rust
Source finding
BUILT BY
tinyhumansai
OpenHuman local-first desktop agent built by developer collective tinyhumansai
Source finding
MENTIONS
Karpathy
OpenHuman is inspired by Karpathy's LLM Knowledgebase concept
Source finding
USES
Obsidian Wiki
OpenHuman uses Obsidian Wiki for local knowledge in Memory Tree.
Source finding
PARTNERS WITH
Obsidian
OpenHuman integrates with Obsidian vault for persistent memory
Source finding

Source trail

Source Source Source Source LibreChat Foundry Local Kilo TechTimes

Graph sources

entity graphfindings textkg edgeskg entitiesnewsletter issues

Fetching from the wire…