aegra-api
Aegra core API - Self-hosted Agent Protocol server
Decision gist · record as of 2026-08-14
Yes, if you need to self-host LangGraph agents and have PostgreSQL infrastructure available. The package is actively maintained, has no known vulnerabilities, and provides a complete Agent Protocol implementation with production-ready features (streaming, cron jobs, observability). Install friction is low. The substantial dependency footprint and requirement for PostgreSQL setup are expected trade-offs for a self-hosted server, not drawbacks. Not suitable if you prefer managed agent hosting or lack infrastructure to run PostgreSQL.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires PostgreSQL database, Python 3.12+, and LangGraph graph definitions in aegra.json configuration file.
- Low install friction with a pure Python wheel.
- Active maintenance: released 2 days ago with 1134 repository stars.
License · maintenance · safety
Apache-2.0 (permissive) — Apache-2.0 permissive license allows commercial use, modification, and redistribution with minimal restrictions, suitable for self-hosted deployments in both open-source and proprietary contexts.
last release 2026-08-12 (2 days) · last repo commit 2026-08-13 · 1,134 stars
0 known vulnerabilities (OSV.dev, 2026-08-14) · 85,991 downloads/mo, #13,890 on PyPI
Alternatives
Verify before relying
# Install
pip install aegra-api
# Set environment variables
export POSTGRES_USER=aegra
export POSTGRES_PASSWORD=aegra_secret
export POSTGRES_HOST=localhost
export POSTGRES_DB=aegra
# Run migrations and start
alembic upgrade head
uvicorn aegra_api.main:app --port 2026 --reload- Whether the package works with Python versions beyond 3.12 despite 'supports_current' classifier.
- Performance characteristics and scalability limits for concurrent agent runs.
- Specific observability integrations beyond LANGFUSE and PHOENIX mentioned in docs.
What it is and what it does
Aegra API is a FastAPI-based server that hosts and executes AI agent graphs defined using LangGraph, providing a self-hosted alternative to vendor-locked services. It implements the Agent Protocol standard, making agents compatible with tools like Agent Chat UI and LangGraph Studio. The package handles agent lifecycle management—creating assistants from graph definitions, managing conversation threads, executing runs synchronously or with streaming, and canceling in-flight executions. It includes built-in support for human-in-the-loop approval workflows and scheduled cron job triggers with timezone awareness and multi-instance safety.
The server stores agent state and conversation history in PostgreSQL, offers semantic search via a vector store, and integrates observability through OpenTelemetry with exporters for tracing and metrics. It requires substantial infrastructure—a PostgreSQL database, Redis for caching, and configured LangGraph agent graphs—making it suited for teams deploying agents on their own servers rather than using managed platforms. The dependency stack includes SQLAlchemy for ORM, Pydantic for validation, and Prometheus instrumentation for monitoring.
Use it for
- Deploy proprietary AI agents on internal infrastructure without reliance on third-party agent hosting platforms.
- Build multi-turn conversation systems with thread-based state management and human approval gates.
- Schedule recurring agent tasks (e.g., daily reports, periodic data processing) with cron-like triggers.
- Integrate LangGraph workflows into production systems via REST API with streaming response support.
- Monitor and trace agent execution with OpenTelemetry observability and Prometheus metrics.
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
Yes, if you need to self-host LangGraph agents and have PostgreSQL infrastructure available.
The package is actively maintained, has no known vulnerabilities, and provides a complete Agent Protocol implementation with production-ready features (streaming, cron jobs, observability). Install friction is low. The substantial dependency footprint and requirement for PostgreSQL setup are expected trade-offs for a self-hosted server, not drawbacks. Not suitable if you prefer managed agent hosting or lack infrastructure to run PostgreSQL.
Install
aegra-api on PyPI
Before you install
Low install friction with a pure Python wheel. Active maintenance: released 2 days ago with 1134 repository stars. Requires 22 runtime dependencies including FastAPI, LangGraph, PostgreSQL drivers, and OpenTelemetry observability stack—a substantial but typical footprint for a production agent server.
Requires PostgreSQL database, Python 3.12+, and LangGraph graph definitions in aegra.json configuration file.
License in practice
Apache-2.0 permissive license allows commercial use, modification, and redistribution with minimal restrictions, suitable for self-hosted deployments in both open-source and proprietary contexts.
Quickstart
# Install
pip install aegra-api
# Set environment variables
export POSTGRES_USER=aegra
export POSTGRES_PASSWORD=aegra_secret
export POSTGRES_HOST=localhost
export POSTGRES_DB=aegra
# Run migrations and start
alembic upgrade head
uvicorn aegra_api.main:app --port 2026 --reloadVerify before relying
- Whether the package works with Python versions beyond 3.12 despite 'supports_current' classifier.
- Performance characteristics and scalability limits for concurrent agent runs.
- Specific observability integrations beyond LANGFUSE and PHOENIX mentioned in docs.
Package facts
| License | Apache-2.0 permissive |
| Python support | Supports the current Python release >=3.12 |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 22 packagesalembicasgi-correlation-idasyncpgcroniterfastapigreenletlanggraph-checkpoint-postgreslanggraph-sdklanggraphopeninference-instrumentation-langchainopentelemetry-apiopentelemetry-exporter-otlpopentelemetry-sdkprometheus-fastapi-instrumentatorpsycopgpydantic-settingspydanticredissqlalchemysse-starlettestructloguvicorn |
| Maintenance | Actively maintained 2 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 85,991 / month, #13,890 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | Development Status :: 4 - BetaFramework :: FastAPIIntended Audience :: DevelopersLicense :: OSI Approved :: Apache Software LicenseProgramming Language :: Python :: 3.12Topic :: Scientific/Engineering :: Artificial Intelligence |
Evidence: aegra_api-0.10.0-py3-none-any.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “self-hosted agent protocol server”
- aegra-apiAegra API is a self-hosted Agent Protocol server that runs AI agent…
- openhands-aiOpenHands is a self-hosted developer control center that runs coding…
- matrix-synapseMatrix Synapse is a homeserver implementation for the Matrix…
Give your agent the search over MCP, or paste the wish link into any chat.
More Artificial Intelligence packages
LiteLLM provides a unified Python interface to call 100+ LLM providers (OpenAI, Anthropic, Gemini, Bedrock, Azure, and others) using OpenAI-compatible API format, available as both a Python SDK and a self-hosted AI Gateway proxy server.
Install it if you need to work with multiple LLM providers or want to centralize LLM routing in your organization.
Client library and CLI tool for downloading, uploading, and managing models, datasets, and repositories on the Hugging Face Hub platform.
Install it if you work with Hugging Face Hub models or datasets.
LangChain provides a framework for building agents and LLM-powered applications by composing language models, tools, and memory through a unified API that abstracts over multiple model providers.
hf-xet provides chunk-based deduplication and efficient file transfer for the Hugging Face Hub, enabling faster uploads and downloads of large files with local disk caching.
Tokenizers converts raw text into token sequences for NLP models, with support for training custom vocabularies and using pre-built tokenizers (BPE, WordPiece) optimized for speed via Rust.
Transformers provides a unified framework for loading, fine-tuning, and running state-of-the-art pretrained models across text, vision, audio, video, and multimodal tasks using PyTorch, JAX, or TensorFlow.
Install it if you need to run or train any transformer-based model for NLP, vision, audio, or multimodal tasks.
See also langgraph-sdk · ag-ui-langgraph · langgraph · langgraph-api · uipath-langchain · langgraph-swarm · langgraph-checkpoint-aws · ag_ui_adk · agent-framework-ag-ui · langgraph-checkpoint-redis