LieGraph - AI Agent-Driven "Who Is Spy" Game. Multi-agent social deduction game built with LangGraph where autonomous AI agents use LLM reasoning to find the spy through conversation analysis and strategic voting.
active 2025-10-26 → 2026-04-08 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 165 days from 2025-10-26 to 2026-04-08. Pushes: 39 total, peak 10 in a day. Pull requests: 9 total, peak 4 in a day. Issues: 1 total, peak 1 in a day. Comments: 13 total, peak 6 in a day. Stars: 16 total, peak 3 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
| Contributor | Contributions | Pushes | PRs | Comments |
|---|---|---|---|---|
| leslieo2 | 56 | 39 | 9 | 7 |
| chatgpt-codex-connector[bot] | 10 | 0 | 0 | 6 |
| jw409 | 1 | 0 | 0 | 0 |
Recent activity
Latest issues, pull requests and releases
- Issue#19jw4092026-04-02 00:37Integration: romancer4 trust hierarchy for agent credibility modeling
- Pull request#18leslieo22025-11-08 10:43
- Pull request#17leslieo22025-11-08 09:32
- Pull request#16leslieo22025-11-08 08:55
- Issue comment#15leslieo22025-11-02 03:00feat: add configurable metrics toggle and guard node hooks
- Issue comment#15leslieo22025-11-02 02:57feat: add configurable metrics toggle and guard node hooks
- Issue comment#15leslieo22025-11-02 02:50feat: add configurable metrics toggle and guard node hooks
- Pull request#14leslieo22025-11-01 03:30
- Pull request#12leslieo22025-11-01 03:00
- Issue comment#9chatgpt-codex-connector[bot]2025-10-31 09:45feat: implement LLM-driven voting strategy with structured tools
- Issue comment#9leslieo22025-10-31 08:50feat: implement LLM-driven voting strategy with structured tools
- Pull request#7leslieo22025-10-29 11:35
- Pull request#6leslieo22025-10-29 09:44
- Issue comment#5chatgpt-codex-connector[bot]2025-10-29 09:34refactor: layer workflow and agent modes with tool-node-graph split
- Issue comment#5leslieo22025-10-29 09:28refactor: layer workflow and agent modes with tool-node-graph split
- Issue comment#4chatgpt-codex-connector[bot]2025-10-29 07:34feat: add configurable vote strategies for agent behavior
- Issue comment#4leslieo22025-10-29 07:30feat: add configurable vote strategies for agent behavior
- Issue comment#3leslieo22025-10-29 04:05feat: implement dual-mode agent architecture with memory and strategy selection
- Pull request#3leslieo22025-10-29 02:54
- Pull request#2leslieo22025-10-29 02:15
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 16 stars here means stars gained during the window, not the repo's star count.