No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by dixiyao · Codex Skill · ★ 112
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is FoT safe to install? View the security audit →
FoT Federation over Text Federation over Text (FoT) is a federated-learning-like paradigm for multi-agent reasoning. Instead of sharing gradients or model weights, agents share reasoning traces distilled from completed tasks. A central aggregation process then organizes and compresses those traces into reusable insights that can help future agents solve related problems more effectively. There are strong connections between FL and FoT. In FL, clients may adopt different optimization methods to solve local subproblems. Analogously, in FoT, each agent may use distinct local reasoning strategies and prompt designs to generate traces. Inspired by techniques from distributed and federated learning, FoT opens an interesting design space for improving the efficiency and effectiveness of multi-agent collaborative reasoning. FoT Runtime FoT is an orchestration framework for Federation over Text (FoT) built on top of . It lets you run multiple OpenClaw agents in parallel, recover their reasoning traces after execution, and aggregate those traces into a persistent shared insight library. The result is a practical testbed fo
| Stars | 112 |
| Forks | 2 |
| Language | Python |
| Category | Codex Skill |
| License | MIT |
| Quality Score | 75.9520683670893/100 |
| Last Updated | 2026-09-29 |
| Created | 2026-04-21 |
| Platforms | python |
| Est. Tokens | ~16k |
These tools work well together with FoT for enhanced workflows:
Looking for a FoT alternative? If you're comparing FoT with other codex skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
🚀 JoySafeter: An enterprise AI Agent Platform—Not just chatting. building、running、testing, and tracing autono
An introduction to the world of AI Agents
Open-source Agentic AI framework in Go for building, orchestrating, and deploying intelligent agents. LLM-agno
Turbo Rig private beta HQ + devcontainer seed — the rig era starts here. Request access: turbo-rig-beta.vercel
Curated awesome list for OpenClaw (formerly Moltbot/Clawdbot): skills, plugins, memory systems, MCP tools, dep
An AI-native OS. Models run on your own hardware, nodes federate peer-to-peer with no broker, and the API is O
Explore other popular codex skill tools:
FoT is Federation over Text (FoT) is a federated-learning-like paradigm for multi-agent reasoning.. It is categorized as a Codex Skill with 112 GitHub stars.
FoT is primarily written in Python. It covers topics such as agentic-ai, federated-learning, multi-agent.
You can find installation instructions and usage details in the FoT GitHub repository at github.com/dixiyao/FoT. The project has 112 stars and 2 forks, indicating an active community.
FoT is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to FoT on Agent Skills Hub include JoySafeter, oreilly-ai-agents, AgenticGoKit. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: