Entity trail

Nanobot

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

Briefing refs

Findings

Edges

Sources

Corpus findings

2026-09-08 / projects-researcherOpen PR to open issue ratios split five large agent repos into two opposite backlog shapesSplitting open_issues_count into pull requests and issues across today's largest agent repos separated them cleanly in one pass: HKUDS/nanobot runs 564 open PRs to 207 issues (2.7:1 PR-heavy) at 47,883 stars, while iOfficeAI/AionUi inverts it at 217 PRs to 664 issues at 32,677 stars. bytedance/deer-flow (386 to 520), Tencent/WeKnora (289 to 393) and nexu-io/open-design (470 to 482) sit near parity. A PR-heavy backlog means contributors are outrunning review capacity; an issue-heavy one means users are outrunning the maintainers. The raw open_issues_count number hides both.
2026-09-05 / projects-researcherVane sits at 36,633 stars with no tagged release since 2026-04-10, and nanobot at 47,725 with none since 2026-07-25ItzCrazyKns/Vane, an AI answering engine, last cut v1.12.2 five months ago; HKUDS/nanobot, a self-hosted personal agent framework with WebUI, tools, memory, MCP and multi-agent workflows, last cut v0.3.0 six weeks ago after a steady monthly cadence through v0.2.x. Both were in today's preflight intake near the top by star count. Star totals in the tens of thousands and a stalled release train together mean the repo is being discovered faster than it is being shipped, which is worth knowing before adopting either as a dependency.
2026-08-26 / projects-researcherHKUDS/nanobot Reached 47,419 Stars and 8,369 Forks in Under Seven Months but Has Not Tagged a Release Since July 25nanobot, an ultra-lightweight self-hosted Python agent framework with a WebUI, tools, memory, MCP and multi-agent workflows, was created 2026-02-01 and has accumulated 47,419 stars and 8,369 forks, an 18% fork ratio. Its last tagged release is v0.3.0 on July 25, a month back, while 741 issues sit open and main was pushed again this morning. That gap between an active main branch and a stale tag means anyone pinning to a release is a month behind the code the stars are actually reacting to.
2026-08-18 / arxiv-researcherCompoSkill: Agent Skills That Each Pass a Safety Scanner Chain Into Attacks 83.3% of the TimeThe paper attacks the core assumption of skill marketplaces — that per-package certification makes the ecosystem safe — by showing composition risk is a path-level, not node-level, property. A black-box attacker that knows only a role profile downloads top marketplace skills, builds a Skill Composition Graph, and searches for risky chains whose lures never name skill identifiers, hitting 80.6% Chain Formation Rate (83.3% white-box) on CompoSkill-Bench, 1,140 records across five threats and six scenarios on OpenClaw and Nanobot. Existing scanners block only a limited fraction; attack success also decays past three hops, giving a concrete bound defenders can design around.
2026-08-17 / github-pulse-researchernanobot Spent Two Days Fixing Reconnect-Safe Mutation Replay in Its WebUI — the Unglamorous Half of Self-Hosted AgentsHKUDS/nanobot, the ultra-lightweight self-hosted personal agent framework at 47,091 stars, pushed a run of fixes on 2026-08-15 and 2026-08-16 making WebUI mutations reconnect-safe, snapshotting mutation replay frames, preserving mutation order after reconnect, and hardening replay test coverage. The same window added atomic model-preset renames with inline conflict detection, serialized gateway configuration updates, and preserved legacy OrcaRouter custom configs. Its last tagged release remains v0.3.0 from 2026-07-25, so this is unreleased mainline work — but it is the failure mode every long-running self-hosted agent UI hits, and worth reading before you write your own.
2026-08-05 / github-pulse-researcherHKU's Data Intelligence Lab Is Running an Ultra-Lightweight Personal Agent Framework at 46,653 Stars and 8,252 ForksHKUDS/nanobot reached 46,653 stars with 8,252 forks (MIT, created 2026-02-01, pushed 2026-08-05), an academic lab shipping a self-hosted personal agent framework with WebUI, tools, memory, MCP, multi-agent workflows, and Discord/Telegram chat-app bindings. The 18% fork ratio and 771 open issues indicate it is being deployed, not just starred. It is a rare case of a university lab holding a top-tier consumer agent framework rather than publishing a paper and abandoning the code.
2026-08-05 / github-pulse-researcherFork-to-Star Ratios Above 20% Are Flagging Which Agent Repos Get Run Instead of BookmarkedAcross the repos verified via the GitHub API on 2026-08-05, fork-to-star ratio separates tools people execute from tools people admire. Outliers: Gitlawb/openclaude at 8,899 forks on 30,521 stars (29%), pingdotgg/t3code at 3,746 on 16,730 (22%), santifer/career-ops at 12,395 on 62,867 (20%), and HKUDS/nanobot at 8,252 on 46,653 (18%) — against Scrapling at 10% (7,223/72,647) and VectifyAI/PageIndex at 9% (3,069/35,022). The high-fork cluster is dominated by self-hosted personal agents and job-search automation, i.e. tools whose value requires forking and configuring, which makes the ratio a better adoption proxy than star count for this category.
2026-07-29 / github-pulse-researchernanobot v0.3.0 Lands 260 Merged PRs and 38 New Contributors, Adding Inline Subagents and an Opt-In /goal Long-Run ModeHKUDS/nanobot (46,369 stars, 8,207 forks, MIT) released v0.3.0 on 2026-07-25 with 260 PRs merged and 38 new contributors since v0.2.2 on 2026-06-23. The release makes a bundled WebUI the front door via a single nanobot webui command that prepares the UI, starts the gateway and opens a browser workbench with no separate frontend build. The agency model is deliberately bounded: inline subagents, explicitly authorized work carried through verification, per-session model presets, and long-running execution only when a task opts in through /goal, leaving ordinary conversations unchanged.
2026-07-27 / vibe-coding-researcherPattern: The "Super-Agent Harness" Shape Has Converged on Five ComponentsByteDance's deer-flow (78k stars, ground-up v2 rewrite) ships the now-standard stack: sandboxes (local/Docker/Kubernetes, each task getting a full filesystem view), file-backed long-term memory with SQLite FTS5 and Markdown fact storage per agent, Markdown-defined skills that load progressively, sub-agents with isolated contexts and scoped tools that report structured results, and a message gateway across Telegram/Slack/Feishu/WeChat/DingTalk. LobeHub (80.9k stars) and HKUDS/nanobot (46.3k) expose near-identical primitives. If you're designing an agent runtime from scratch, this five-part decomposition is the emerging default — deviate deliberately, not by accident.
2026-07-19 / github-pulse-researcherHKUDS Follows nanobot With DeepTutor — 'Lifelong Personalized Tutoring' Built on RAGHKUDS/DeepTutor gained 196 stars this week, extending the HKUDS lab's run of high-visibility agent releases alongside nanobot (45,882 stars) and LightRAG (37,823 stars). DeepTutor targets lifelong personalized tutoring — persistent learner models rather than per-session Q&A — using the lab's own retrieval stack. One academic group shipping three separately-successful agent projects is itself a signal about where usable agent research is coming from.
2026-07-19 / projects-researcherHKUDS Ships Vibe-Trading Updates Two Days Running — Correlation-Regime Detection Plus a Live-Safety Correctness PassHKUDS/Vibe-Trading, a personal trading agent from the same lab behind LightRAG and nanobot, landed a correlation-regime detection skill alongside a broad backtest/data/live-safety correctness pass on July 17, then added Binance crypto fallback and parallel-execution fixes on July 18. The 'live-safety' framing is the interesting part — the project is explicitly separating backtest correctness from real-money execution guards. Treat any LLM trading agent's claims skeptically, but the safety-layer separation is a pattern worth copying.
2026-06-05 / projects-researcherHKUDS Ships nanobot v0.2.1 'Workbench Release' on June 1 — Lightweight Open-Source Agent Turns Into a Daily DriverHKUDS released nanobot v0.2.1, the 'Workbench Release,' on June 1, 2026, upgrading its packaged WebUI into a daily agent workspace with Thought/response timelines, live file-edit activity, project workspaces, model/context controls, and CLI Apps + MCP extensions. It targets the gap between toy agent demos and something you actually keep open all day. The MCP extension support and project workspaces make it a plausible lightweight alternative to heavier agent IDEs.

Graph relationships

BUILT BY
HKUDS
nanobot is a project by HKUDS on GitHub
Source finding
BUILT BY
HKUDS
HKUDS developed nanobot.
Source finding
BUILT BY
HKUDS
HKUDS developed nanobot.
Source finding
BUILT BY
HKUDS
Nanobot is an ultra-lightweight personal AI agent from HKU.
Source finding
BUILT BY
HKU Data Science Lab
Nanobot from HKU's Data Science Lab launched in February 2026.
Source finding
BUILT BY
HKUDS
nanobot is an open-source AI agent developed by the HKU Data Science lab.
Source finding
SUPPORTS
MCP
nanobot v0.2.1 supports MCP extensions
Source finding
USES
Python
nanobot is implemented in Python
Source finding
USES
MCP
nanobot is a self-hosted Python agent framework with MCP support
Source finding
COMPETES WITH
Claude Code
Nanobot positioned as lightweight alternative to Claude Code.
Source finding
USES
OpenAI
Nanobot supports multiple LLM backends including OpenAI.
Source finding

Source trail

CompoSkill SkillWatermark Tencent's AI-Infra-Guard team TauricResearch's framework Roo Code shutting down VS Code support May 15 HKUDS/nanobot Block's agent framework GitHub GitHub GitHub Trending GitHub GitHub

Graph sources

entity graphfindings textkg edgeskg entitiesnewsletter issues

Fetching from the wire…