Repository profile
Stress-test AI agents for goal drift and system prompt violations. Inspired by 'Asymmetric Goal Drift in Coding Agents' (ICLR 2026).
Repository updates
Get generated jhammant/agent-drift development summaries by email, or follow the weekly and monthly RSS feeds.
Sign in to subscribe by email. RSS feeds are public.
Sign in to subscribeTracked growth, recent movement, and commit velocity from stored repository snapshots.
Latest capture 2026-07-15 03:03
5 captures since 2026-05-25
Stars from baseline 0
All tracked data
Frameworks, package managers, ecosystems, and dependency manifests found during catalog scans.
Scanned 2026-07-15 03:03
pyproject.toml
python ecosystem,
4 dependencies
Searchable topics, generated tags, and stack labels that explain where this repository fits.
Agent instructions and tool configuration paths found in the repository tree.
Nearest indexed repositories by embedding similarity.
The linter for your agent harness. Works with Claude Code, Codex, and Cursor.
Independent verification for coding agents. A change isn't done until a different model or a real test checks it, and the verdict is recorded in your repo.
Self-tuning multi-agent AI trading system. 8-source signal fusion (Polymarket + Kalshi + 10 ML models incl. Kronos foundation model), Bull/Bear/Judge debate on Claude Opus 4.7, Portfolio Manager gate.
Pre-execution governance for AI agents. Sub-millisecond tool call validation, drift detection, circuit breakers, human-in-the-loop holds. 829 tests. 56 MCP tools.
A framework-agnostic, git-native standard for defining AI agents
Open-source, end-to-end platform for evaluating, observing, and improving LLM and AI agent applications. Tracing · Evals · Simulations · Datasets · Gateway · Guardrails. Self-hostable. Apache 2.0.
