by antoinezambelli · Agent Tool · ★ 2.3k
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
pip install forge-guardrails # core only
pip install "forge-guardrails[anthropic]" # + Anthropic clientTaken from the project's README on GitHub. Check the security audit before running it.
None of the 42 rules matched — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against 42 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
The quality score combines nine heuristic checks of the repo and its README: completeness, clarity, specificity, examples, structure, agent readiness, step-by-step content, instruction quality and security notes. It rates how well the project explains itself to an agent, not the code.
| Stars | 2,264 |
| Forks | 174 |
| Language | Python |
| Category | Agent Tool |
| License | MIT |
| Quality Score | 69/100 |
| Open Issues | 3 |
| Last Updated | 2026-11-02 |
| Created | 2026-02-16 |
| Platforms | python |
| Est. Tokens | ~16k |
forge A reliability layer for self-hosted LLM tool-calling. Forge lifts an 8B local model to the top of its class on multi-step agentic workflows through guardrails (rescue parsing, retry nudges, step enforcement) and context management (VRAM-aware budgets, tiered compaction).
Looking for a forge alternative? If you're comparing forge 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.
The Ruby-native AI framework. Chats, agents, tools, images, audio, and video through one consistent API, in pl
A set of tools that gives agents powerful capabilities.
Agent samples built using the Strands Agents SDK.
🚀 Universal SDK for building next-gen MCP servers
Browser Operator - The AI browser with built in Multi-Agent platform! Open source alternative to ChatGPT Atlas
The python library for research and development in NLP, multimodal LLMs, Agents, ML, Knowledge Graphs, and mor
Explore other popular agent tool tools:
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 42 published rules, covering credential harvesting, data exfiltration, curl | sh installers and more. 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: