Capframe – capability tokens and policy enforcement for AI agent tool calls
Capframe has released version 0.2.0, focusing on capability tokens and policy enforcement for AI agents. The tool includes three Rust modules that enhance security by mapping tool surfaces, binding authority, and guarding tool calls. It is designed to comply with major security frameworks and is available as an open-source solution.
- ▪Capframe provides a structured approach to securing AI agent tool calls through discovery, authority binding, and enforcement.
- ▪The tool is compliant with OWASP, NIST, and MITRE frameworks, ensuring audit-ready artifacts.
- ▪Capframe is open-source and offers a hosted version for teams needing advanced features.
Hacker News (AI / LLM) files mainly under ai. We currently carry 3,323 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Story provenance
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | Capframe |
| Canonical URL | https://capframe.ai |
| Publication time | Tue, 19 May 2026 23:46:47 +0000 |
| Retrieval time | 2026-05-19T23:49:58.582Z |
| Last seen | 2026-05-19T23:49:58.582Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | HRUEfMnHnLCG |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
v0.2.0 releasedAI agent securityCapability securityfor AI agents.Three Rust modules for AI agents that call tools. Find what they touch. Bind their authority. Guard every call. MCP-native. Audit-mapped to OWASP LLM, NIST AI RMF, MITRE ATLAS. MIT licensed.Install Capframe→ Star on GitHub$curl -fsSL capframe.ai/install | sh~/agents — capframe install$ capframe install → mcp-recon ✓ mcp-recon v0.0.4 sha256 ok · 1.2 MB → capnagent ✓ capnagent v0.7.6 sha256 ok · 1.2 MB → mcp-guard ✓ mcp-guard v0.5.4 sha256 ok · 19.9 MB Verify with: capframe doctor Add to PATH: ~/.capframe/bin§ 01The pipelineFour stages. One binary. No LLM in the decision path.01DiscoveryFindMap the tool surface.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at Capframe.
Discussion
0 commentsMore from Capframe
