SwarmAuth – OAuth 2.1 for AI Agent Swarms
SwarmAuth is an open-source authorization standard designed for autonomous AI agent swarms, utilizing OAuth 2.1 principles to issue cryptographically signed, short-lived delegation tokens. The system addresses the security risks of prompt injection by enforcing capability-scoped limits and strict expiration times, ensuring that compromised LLMs cannot execute unauthorized actions. It supports multi-agent environments through features like key rotation and atomic usage tracking via Redis, while maintaining minimal dependencies and sub-millisecond verification speeds.
- ▪SwarmAuth issues delegation tokens with a maximum time-to-live of 300 seconds to limit the window of potential abuse.
- ▪The library uses Ed25519 signatures and Pydantic for schema validation, avoiding heavy external dependencies in its core.
- ▪KeyRegistry allows for the management of multiple issuers and supports key rotation without invalidating in-flight tokens.
- ▪RedisUsageTracker enables atomic enforcement of rate, budget, and call limits across multiple verifier processes in a distributed swarm.
- ▪Framework adapters are provided for LangChain, CrewAI, AutoGen, and MCP tools to facilitate easy integration into existing AI stacks.
Hacker News (AI / LLM) files mainly under ai. We currently carry 5,587 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 | PyPI |
| Canonical URL | https://pypi.org/project/swarmauth/ |
| Publication time | Sat, 19 Sep 2026 09:28:20 +0000 |
| Retrieval time | 2026-09-19T09:33:45.990Z |
| Last seen | 2026-09-19T09:33:45.990Z |
| 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 | MopV_ut4sn45 · 1 stories |
| 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
swarmauth 0.1.1 OAuth 2.1 for autonomous AI agent swarms: signed, short-lived, capability-scoped delegation tokens. pip install swarmauth Copy PIP instructions Description Release files Release history SwarmAuth The zero-trust authorization standard for multi-agent systems. SwarmAuth is OAuth 2.1 for autonomous AI swarms: cryptographically signed, short-lived (≤300s), capability-scoped delegation tokens for agent-to-agent and agent-to-tool calls. It's built on one assumption you should already hold — your LLM layer will be compromised by prompt injection — and asks a different question: when that happens, does the execution boundary stop the damage, or does it just trust whatever the model decided? Today, most multi-agent stacks pass raw API keys or unscoped bearer tokens between agents.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at PyPI.
Discussion
0 commentsMore from PyPI
