AgentQuant AI Agent

by OnePunchMonk• 218•• Scanned•Claim this listing•Request removal
Finance & Tradingagentic aiautonomous agentfinance aifintechharness engineering

A failure-aware harness for reproducible quantitative-strategy research, with typed agent workflows and inspectable experiment memory.

AgentQuant is an open-source ai agent by OnePunchMonk, written mainly in Python, with 218 GitHub stars and the MIT license. Its code was last updated Oct 28, 2026.

Scan summary: scanned Nov 5, 2026 at commit 97ebf4d. No capabilities flagged by our checks. Scan policy

What AgentQuant can touch

  • Run shell commandsNot seen in this scan
  • Run dynamic codeNot seen in this scan
  • Read or write filesNot seen in this scan
  • Read environment and secretsNot seen in this scan
  • Control a web browserNot seen in this scan
  • Connect to databasesNot seen in this scan
  • Read or send messagesNot seen in this scan
  • Touch money or tradingNot seen in this scan
  • Connect to the internetNot run in this scan

"Not seen" means our checks did not find it, and the tool may still do it. Covers commit 97ebf4d, Nov 5, 2026. See the scan policy.

Before you install AgentQuant

AgenticMart scanned AgentQuant on Nov 5, 2026 with automated checks for hidden code, known-malicious packages, leaked secrets and vulnerable dependencies. The result covers one commit under our scan policy, so review what access you give it and check any advisories shown here.

What it can access

  • An AI agent decides its own next steps and calls whatever tools you give it, so its risk depends on the access you grant.
  • Based on its description and topics, it likely needs to touch financial accounts or data.

Before you install

  1. Never give it live trading or payment keys until you've read the code.
  2. Pin the version you reviewed instead of always installing the latest release.
  3. Read the tool list or scripts before the first run, and keep approval prompts on for actions that write, send or delete.
  • Maintained by OnePunchMonk on GitHub, 218 stars and 46 forks. Popularity is not proof of safety.
  • Last code change: Oct 28, 2026.
  • Open-source license: MIT.

AgentQuant is an open-source ai agent by OnePunchMonk, written mainly in Python. A failure-aware harness for reproducible quantitative-strategy research, with typed agent workflows and inspectable experiment memory.

At a glance

Stars
218
Forks
46
Language
Python
License
MIT
Created
Aug 2025
Last update
Oct 28, 2026
Type
AI Agent
Price
Free

Topics

agentic-aiautonomous-agentfinance-aifintechharness-engineeringlangchainlanggraphllm-agentsportfolio-optimizationquant-agentquantitative-financequantitative-researchreact-agentself-evolving-agentsself-improving-aistock-aivectorbtyfinance

Questions about AgentQuant

What is AgentQuant?

A failure-aware harness for reproducible quantitative-strategy research, with typed agent workflows and inspectable experiment memory.

Who maintains AgentQuant?

AgentQuant is maintained by OnePunchMonk on GitHub (OnePunchMonk/AgentQuant). AgenticMart lists it from public repository data.

Is AgentQuant safe to use?

AgenticMart scanned AgentQuant on Nov 5, 2026 with automated checks for hidden code, known-malicious packages, leaked secrets and vulnerable dependencies. The result covers one commit under our scan policy, so review what access you give it and check any advisories shown here.

What license does AgentQuant use?

It is published under the MIT license.

AgentQuant alternatives

View more →

Similar ai agents in Finance & Trading, ranked by GitHub stars. Compare licence, recent activity and scan status before you choose.

NameStarsLicenceLast updatedScan
AgentQuant (this page)
OnePunchMonk
218MITOct 28, 2026Scanned, no flagged issues
Daily Stock Analysis
ZhuLinsen
67kMITOct 31, 2026Scanned, no flagged issues
Vibe Trading
HKUDS
37kMITOct 30, 2026Scanned, no flagged issues
FinceptTerminal
Fincept-Corporation
33kNone foundOct 26, 2026Not scanned yet
A Stock Data
simonlin1212
11kApache-2.0Oct 30, 2026Scanned, no flagged issues
Bindu
GetBindu
10kNone foundSep 6, 2026Not scanned yet