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 Agent-Field · Agent Tool · ★ 95
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is af-deep-research safe to install? View the security audit →
AF Deep Research Autonomous research backend for AI applications. Early Preview · APIs may change. Feedback welcome. A research API that questions itself. Submit a query. The system spawns parallel agents, evaluates what it found against quality thresholds, generates new sub-queries when gaps are detected, and runs another cycle. The architecture orchestrates 10,000 logical agent invocations per research. This is an AI backend, not a chat interface. Built on top of agentfield runtime for orchestrating the agents. One-Call DX Trigger it with the CLI (requires af ≥ 0.1.87) — it streams live progress and prints the result: bash af call metade
| Stars | 95 |
| Forks | 21 |
| Language | Python |
| Category | Agent Tool |
| License | Apache-2.0 |
| Quality Score | 66.5090387189793/100 |
| Last Updated | 2026-06-01 |
| Created | 2026-01-06 |
| Platforms | claude-code, python |
| Est. Tokens | ~530k |
Looking for a af-deep-research alternative? If you're comparing af-deep-research with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Automated loop driver, slash commands, council automation, MCP browser bridge, and portfolio governance for Cl
HeyClaude (formerly Claude Pro Directory) is a searchable collection of pre-built AI skills, agents, MCP serve
Self-hosted framework for orchestrating fleets of specialist AI agents — ensemble reasoning and a full agentic
Open source AI coding platform with Web IDE, multi-agent system, 37+ tools, MCP protocol. MIT licensed.
Run LLM prompts from your shell
An example agent demonstrating streaming, tool use, and interactivity from your terminal. This agent builder c
Explore other popular agent tool tools:
af-deep-research is Autonomous AI backend for deep research AI applications.. It is categorized as a Agent Tool with 95 GitHub stars.
af-deep-research is primarily written in Python. It covers topics such as agentfield, agentic-ai, ai-agents.
You can find installation instructions and usage details in the af-deep-research GitHub repository at github.com/Agent-Field/af-deep-research. The project has 95 stars and 21 forks, indicating an active community.
af-deep-research is released under the Apache-2.0 license, making it free to use and modify according to the license terms.
The top alternatives to af-deep-research on Agent Skills Hub include intellegix-code-agent-toolkit, claudepro-directory, captain-claw. 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: