Skip to content

🛠️ DeepAgent: A General Reasoning Agent with Scalable Toolsets

Python · active 2025-10-262026-06-08 (UTC)

Partial coverage11,536 / 12,623 hourly files (91%) · 2 absent upstream · 1,083 failed, retryable2025-03-022026-08-10 (UTC)— sampled evenly across the window, so rankings and trends hold; absolute counts scale up.
Events
398
Pushes
14
Pull requests
4
Issues
8
Stars
360
Forks
4

Activity over time

Daily event counts in the loaded window

Line chart, 226 days from 2025-10-26 to 2026-06-08. Pushes: 14 total, peak 6 in a day. Pull requests: 4 total, peak 1 in a day. Issues: 8 total, peak 1 in a day. Comments: 7 total, peak 2 in a day. Stars: 360 total, peak 43 in a day.

  • Pushes
  • Pull requests
  • Issues
  • Comments
  • Stars

Stars, PRs, issues and forks are under-captured in the later part of this window. GH Archive progressively stopped capturing non-push events during 2026 — −95% or worse by the end of the window. Every series here except Pushes fades for that reason, so a decline above reflects the archive, not this repository. Pushes stay reliable throughout, so read them, and the contributor counts derived from them, as the real signal. Data health has the measurements.

Top contributors

Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity

ContributorContributionsPushesPRsComments
sunnynexus201405
gearupsmile2001
onestardao2010
dongguanting2020
csuJC1000
kiucho1000
tsrigo1000
kris3301001
liaoning971000
JohnHerry1000
Tuesdaythe13th1010

Recent activity

Latest issues, pull requests and releases

  • Issue#17JohnHerry2026-03-17 01:21
    What is the difference with OpenClaw on design philosophy of this project?
  • Pull request#15onestardao2026-02-23 07:36
  • Issue comment#14sunnynexus2026-02-22 10:14
    Proposal: add a small “multi-tool agent failure modes” troubleshooting note (docs only)
  • Issue#14onestardao2026-02-19 09:10
    Proposal: add a small “multi-tool agent failure modes” troubleshooting note (docs only)
  • Pull request#12Tuesdaythe13th2026-01-18 00:59
  • Issue#11liaoning972025-12-17 02:32
    DeepAgent-32B-Base
  • Issue comment#5kris3302025-11-21 07:50
    Open-sourced Training Code
  • Issue#8sunnynexus2025-11-19 03:39
    question regarding the reward calculation with context folding
  • Issue comment#10sunnynexus2025-11-13 03:01
    Question about DeepAgent-32B-Base
  • Issue comment#9sunnynexus2025-11-13 02:56
    question about the evaluation of alfworld
  • Issue#10kiucho2025-11-13 02:17
    Question about DeepAgent-32B-Base
  • Issue comment#7sunnynexus2025-11-10 02:00
    Questions about how to let the auxiliary LLM give simulating rewards for tool calling while training.
  • Issue#7csuJC2025-11-08 15:48
    Questions about how to let the auxiliary LLM give simulating rewards for tool calling while training.
  • Issue comment#5sunnynexus2025-11-06 09:34
    Open-sourced Training Code
  • Issue#6tsrigo2025-11-03 12:56
    Clarification needed on ToolPO reward and "w/o Tool Simulation" ablation
  • Pull request#4dongguanting2025-11-02 04:38
  • Pull request#3dongguanting2025-10-31 04:58
  • Issue comment#2gearupsmile2025-10-28 22:37
    Question: Emotional context in memory folding
  • Issue#2gearupsmile2025-10-28 19:23
    Question: Emotional context in memory folding

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 360 stars here means stars gained during the window, not the repo's star count.