For AI agents: the docs index is at /llms.txt. Every page has a markdown version: add .md to the URL.

Agent Coach
Security scan: passRepoRSection: DeveloperCdLicense: LGPL-3.0LGP

Prediction Market Agent Tooling (Gnosis)

Gnosis Python library to benchmark, deploy and monitor prediction-market agents: AbstractBenchmarkedAgent vs crowd wisdom on Manifold/etc., DeployableTraderAgent base class, and monitoring hooks (GCP optional).

Scan
Vetted pass
GitHub stars
65
Last updated
2026-04-22
License
LGPL-3.0
Cost
needs-key
Why it helps

Gives a capital-forecasting agent a first-party Gnosis harness to score its research/predict loop against the crowd on real markets before any real bets, instead of hand-rolling benchmarks.

Ask your owner first. cost: needs-key; needs a key or account; installs a repo

Paste to your agent

Read https://upskill.coach/repos/prediction-market-agent-tooling.md. If the security scan passed, ask me before installing, then install it with the command under Install and tell me what you did.

Install

poetry install (Python >=3.10); set MANIFOLD_API_KEY / OPENAI_API_KEY in .env. See https://prediction-market-agent-tooling.readthedocs.io/

Community

– views– downloads– comments

Helps with

DeveloperSalesResearchFinance & tradingEvals & qualityCapital & forecastingQuality verificationDeploy & release
Security-scanned on 2026-11-06 at commit 817117d9e5b9: pass.
Scan notes
Automated scan: pass (medium 1) at commit 817117d9e5b9 on 2026-11-06.
Source
github.com/gnosis/prediction-market-agent-tooling
Repo
gnosis/prediction-market-agent-tooling

Static scan at a pinned commit (prompt-injection, malware and exfiltration rules plus semgrep, gitleaks, osv-scanner); flagged lines reviewed by hand. A scan lowers risk; it doesn't prove safety.

Alternatives

Compare all

For agents: markdown, JSON.

Comments

Comments are from visitors, not reviewed by Upskill, and never shown to agents.