Board Position

#1 · AI coding still leads, while agent products are starting to break out.

NEW

deer-flow is currently ranked #1 on the Momentum board. First time on the board. Active window: 24h.

Score99
Confidence78%
Surge+6%
Sourcesgithub
agentagentic

Reading Flow

Keep reading along this board

There are 14 results in the current filtered view. Staying in the same context makes it easy to compare neighboring tools and movement changes.

PreviousAlready near the top

There are no higher-ranked results before this tool in the current view.

Next#2 autogen

A programming framework for agentic AI

Tool Detail

deer-flow

Agent Tools

deer-flow

An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of tasks that could take minutes to hours.

Visit website
Agent ToolsGitHubagentagenticagentic-frameworkgithub
Signal Read 1

deer-flow appears on 2 boards right now, with the primary position at #1 on Momentum.

Signal Read 2

This signal is supported by GitHub, spanning 1 source directions.

Signal Read 3

The system has tracked this tool for 33 runs, first seen Apr 18, 14:25 and most recently updated Oct 15, 23:26.

Score99
Weekly growth+6%
Confidence78%
Primary statusMomentum #1

NEW · First time on the board

Discovery statusRanked

Pool score 99, based on 1 contributing sources.

Tracked runs33

First seen Apr 18, 14:25, last updated Oct 15, 23:26.

Source coverage1

GitHub

7-day score trend
GitHub signals are derived from stars, forks, watchers, and recent activity.
D1
D2
D3
D4
D5
D6
D7
7-day rank movement
Lower numbers are closer to the top
#1D1
#1D2
#1D3
#1D4
#1D5
#3D6
#1D7
Signal summary

deer-flow appears on 2 boards right now, with the primary position at #1 on Momentum.

This signal is supported by GitHub, spanning 1 source directions.

The system has tracked this tool for 33 runs, first seen Apr 18, 14:25 and most recently updated Oct 15, 23:26.

Discovery assessment
Discovery originPrimary provider

1 sources contributed to the candidate judgement.

Candidate typeProduct candidate

Currently in the Ranked stage.

Quality score87

Higher scores usually indicate a real product rather than editorial or noisy content.

Manual ruleAutomatic

No manual rule is active, so the system judgement is still automatic.

Text looks more like product copy: agent, toolIncludes product-like sourcesSource copy looks product-like: agent
System judgement

This section shows how source page evidence, multi-run stability, and auto-promotion logic are combined into the candidate judgement.

Source page evidence+7

1 matched

Stability6 consecutive runs

watchlist 6 · ranked 6 · strong 6

Recent snapshotBest 99

Last seen Oct 14, 08:00

Why the system thinks so

Source page evidence: Source copy looks product-like: agent

Board footprint
Momentum#1
NEW

First time on the board

Score 99Confidence 78%Surge +6%
Newcomers#12
NEW

First time on the board

Score 99Confidence 78%Surge +6%
Why it matters now
  • GitHub is showing a clear upward signal and is worth adding to the watchlist first.
  • Current category: Agent Tools. A good fit for the watchlist.
  • Current board score: 99. A useful starting point for the next round of real-data validation.
What could make it noisy
  • The signal still mainly comes from a single source, so more cross-validation is recommended.
  • This is still a short-window snapshot and lacks longer-term real history.
Source timeline
2026-10-15 23:25

Stars 83914 / Forks 11696 / Watchers 338 / Issues 944 / Active 0d

Cached source page
Source page evidence

This panel aggregates source pages the system has already fetched and cached, so you can judge whether the tool points to a real product site, an editorial page, or just a seed domain.

1 pages
Cached pages1

Total number of fetched pages that are currently available to display.

Successful pages1

Pages fetched successfully with a readable title and summary.

Failed / stale0 / 0

Failed pages will be retried, and stale pages will be refreshed in later syncs.

Domains covered1

Broader domain overlap usually suggests the signal is not just isolated noise.

Status filter

Showing 1 / 1 pages

Sorted by fetch success, freshness, and summary richnessHigh value · 1
Raw signals
GitHubNewcomers #12
Oct 15, 23:26

An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of tasks that could take minutes to hours.

NEWScore 99Confidence 78%Surge +6%
GitHubagentagentic
Matching page evidenceView crawl detailSnapshot live-20261015232644591157-a8bf73Open source
GitHubMomentum #1
Oct 15, 23:26

An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of tasks that could take minutes to hours.

NEWScore 99Confidence 78%Surge +6%
GitHubagentagentic
Matching page evidenceView crawl detailSnapshot live-20261015232644591157-a8bf73Open source
GitHubNewcomers #9
Oct 14, 08:00

An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of tasks that could take minutes to hours.

NEWScore 76Confidence 78%Surge +8%
GitHubagentagentic
Matching page evidenceView crawl detailSnapshot live-20261014080044885074-067a7eOpen source
GitHubMomentum #3
Oct 14, 08:00

An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of tasks that could take minutes to hours.

NEWScore 76Confidence 78%Surge +8%
GitHubagentagentic
Matching page evidenceView crawl detailSnapshot live-20261014080044885074-067a7eOpen source
GitHubNewcomers #12
Oct 13, 23:55

An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of tasks that could take minutes to hours.

NEWScore 99Confidence 78%Surge +6%
GitHubagentagentic
Matching page evidenceView crawl detailSnapshot live-20261013235550780044-4b752dOpen source
GitHubMomentum #1
Oct 13, 23:55

An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of tasks that could take minutes to hours.

NEWScore 99Confidence 78%Surge +6%
GitHubagentagentic
Matching page evidenceView crawl detailSnapshot live-20261013235550780044-4b752dOpen source
GitHubNewcomers #11
Oct 13, 07:45

An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of tasks that could take minutes to hours.

NEWScore 99Confidence 78%Surge +6%
GitHubagentagentic
Matching page evidenceView crawl detailSnapshot live-20261013074514254525-11567bOpen source
GitHubMomentum #1
Oct 13, 07:45

An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of tasks that could take minutes to hours.

NEWScore 99Confidence 78%Surge +6%
GitHubagentagentic
Matching page evidenceView crawl detailSnapshot live-20261013074514254525-11567bOpen source
GitHubNewcomers #11
Oct 5, 07:40

An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of tasks that could take minutes to hours.

NEWScore 99Confidence 78%Surge +6%
GitHubagentagentic
Matching page evidenceView crawl detailSnapshot live-20261005074053805549-a5a304Open source
GitHubMomentum #1
Oct 5, 07:40

An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of tasks that could take minutes to hours.

NEWScore 99Confidence 78%Surge +6%
GitHubagentagentic
Matching page evidenceView crawl detailSnapshot live-20261005074053805549-a5a304Open source
GitHubNewcomers #10
Oct 5, 05:39

An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of tasks that could take minutes to hours.

NEWScore 99Confidence 78%Surge +6%
GitHubagentagentic
Matching page evidenceView crawl detailSnapshot live-20261005053933437285-d0ffccOpen source
GitHubMomentum #1
Oct 5, 05:39

An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of tasks that could take minutes to hours.

NEWScore 99Confidence 78%Surge +6%
GitHubagentagentic
Matching page evidenceView crawl detailSnapshot live-20261005053933437285-d0ffccOpen source
Peer comparison
autogen+1%A programming framework for agentic AI
openai-agents-python+1%A lightweight, powerful framework for multi-agent workflows
GitHub Status - Incident HistoryCandidateGitHub Status - Incident History has been publishing fresh updates consistently through its official content feed.