Aegis
PulseGate's liveness check found it on 6 Oct 2026; it has been in the index since 5 Sep 2026. How this is checked
Aegis is a self-hosted security sidecar for AI agents that intercepts tool calls and enforces allowlists, RBAC, sequence, intent, signature, and human-approval policies. Its Rust data plane, eBPF/LSM controls, flow-taint detection, and signed evidence records support enterprise and air-gapped deployments.
Inferred · not functionally tested
Overview
6 featuresPurpose: Preventing AI agents from making unauthorized tool calls, accessing restricted resources, or leaking sensitive data.
Inferred · not functionally tested
Audience: teams operating OpenAI-compatible AI agents and enterprise security teams
Inferred · not functionally tested
Functions: agents, monitoring, data_extraction
Inferred · not functionally tested
Interfaces: API: indicated (inferred, not tested) · MCP: unknown · CLI: unknown · Self-hosting: indicated (inferred, not tested)
Recorded constraints: pricing: free · license: Proprietary · platforms: WEB · deployment: browser, self_hosted, cloud_managed, api_only
Constraint provenance is unknown; confirm requirements with the publisher.
Record sources: aegiscruc.io. These links do not verify the individual claims.
In the AI security & guardrails space, Aegis takes a focused approach. Inferred · not functionally tested: It focuses on preventing AI agents from making unauthorized tool calls, accessing restricted resources, or leaking sensitive data. Inferred · not functionally tested: Aegis is a B2B product aimed at teams operating OpenAI-compatible AI agents and enterprise security teams. Basis unknown · not verified: Aegis is free to use. Basis unknown · not verified: It runs on the web and API, and it can be self-hosted.
Inferred · not functionally tested: Key capabilities include tool-call interception, HTTP 403 denial, and RBAC policies. Inferred · not functionally tested: Catalogued interfaces include a public API.
Summary written by a language model from the project’s public pages.
Tasks: Inferred · not functionally tested
- Tool-call interception
- HTTP 403 denial
- RBAC policies
- Intent validation
- Human approval holds
- eBPF sandboxing
Topics: Inferred · not functionally tested
Built with & integrations
- Next.js
- x-nextjs-cache header · x-nextjs-prerender header · /_next/static/ in the HTML
- Railway
- x-railway-edge header · x-railway-request-id header
Trust & compliance
Indexing history
1What PulseGate has recorded for this listing
- Indexed5 Sep · 08:09 UTCAegis – Inline security sidecar and eBPF sandbox for LLM agents seen via Hacker News firehose (Algolia)Source: Hacker News firehose (Algolia) · Open
Frequently asked questions about Aegis
- What is Aegis?
- Inferred · not functionally tested: Aegis focuses on preventing AI agents from making unauthorized tool calls, accessing restricted resources, or leaking sensitive data. It is catalogued under AI security & guardrails on PulseGate.
- Who is Aegis for?
- Inferred · not functionally tested: Aegis is a B2B product built for teams operating OpenAI-compatible AI agents and enterprise security teams.
- Is Aegis free?
- Basis unknown · not verified: Yes — Aegis is free to use.
- What platforms does Aegis run on?
- Basis unknown · not verified: Aegis runs on the web and API. It can also be self-hosted.
- Is Aegis still active?
- PulseGate's liveness check found it on 6 Oct 2026.
- What projects are similar to Aegis?
- Similar projects tracked by PulseGate include aegis-sandbox, aegis-security, and Aegisloop.aegis-sandboxaegis-securityAegisloop
- Does Aegis have an API or integrations?
- Inferred · not functionally tested: Yes — Aegis exposes a public API.
Similar projects
Closest matches by what these projects do