Aegra
- 97 installs
- docs.aegra.dev
Helps you deploy and self-host AI agents on Aegra, an open-source Agent Protocol server that is a drop-in alternative to LangSmith Deployments with full data ownership.
About
Aegra is an open-source, self-hosted server for deploying AI agents on the Agent Protocol standard, positioned as a drop-in alternative to LangSmith Deployments with full infrastructure control and data ownership. This skill guides a solo builder through deploying LangGraph agents with persistent state, streaming, configurable auth and OpenTelemetry observability when they want production agent hosting without vendor lock-in.
- Self-hosted Agent Protocol server
- Drop-in alternative to LangSmith Deployments
- PostgreSQL persistence with pgvector
- JWT/OAuth/Firebase auth and OpenTelemetry observability
Aegra by the numbers
- 97 all-time installs (skills.sh)
- Ranked #4,486 of 16,546 AI & Agent Building skills by installs in the Skillselion catalog
- Data as of Jul 29, 2026 (Skillselion catalog sync)
npx skills add https://github.com/docs.aegra.dev --skill aegraAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 97 |
|---|---|
| Repository | docs.aegra.dev ↗ |
What it does
Helps you deploy and self-host AI agents on Aegra, an open-source Agent Protocol server that is a drop-in alternative to LangSmith Deployments with full data ownership.
Who is it for?
Self-hosting production AI agents with data ownership
Skip if: Quick throwaway prototypes
When should I use this skill?
Deploying agents to your own infrastructure
Related skills
Setup Matt Pocock SkillsScaffold the per-repo configuration that Matt Pocock’s engineering agent skills rely on so they understand the issue tracker, triage labels, and domain documentation la495k196k
Lark AppsConnect Claude, Cursor or custom agents directly to Lark (Feishu) for messaging, document automation, approval workflows and enterprise data access.402k
CavemanSlash token usage by roughly 75% while keeping every technical detail intact when working with Claude Code, Cursor or similar agents.391k94.7k
Lark Skill MakerQuickly turn any Lark/Feishu OpenAPI call or multi-step workflow into a reusable agent skill with its own SKILL.md.386k16k
Running Claude Code Via Litellm CopilotRun Claude Code at a fraction of the cost by routing requests through LiteLLM to the GitHub Copilot Chat API.270k72
Codex PetGenerate a complete Codex Pet spritesheet and metadata from one reference image without needing an OpenAI key or Codex Pro.246k10