Hector Agent Runtime
A self-hosted Go runtime for configuring, running, and operating A2A-compatible AI agents from YAML or Studio.
- Source repo
- verikod/hector
- Stars
- ★ 60
- Last updated
- 6mo ago
- License
- MIT
- Primary language
- Go
- FA score
- 65/100 · Some gaps
At a glance
- How it runs
- Works with
- Universal · cross-platformOpenAI API · Claude API
- Cost
- Free software; you pay for model usage
- Setup effort
- Low · running in minutes
- You'll need
- Typical use
- A platform team needs to run an agent service on-premise, in an air-gapped network, or in its own cloud with a single binary and locally controlled credentials.
- Not a fit if
- Teams unwilling to run their own database: PostgreSQL must be supplied and operated
- Teams needing HA, backup, or sizing docs: the material does not cover them
- Source review
- 65/100 · Some gaps
What does this agent do, and when should you use it?
Hector is an open-source AI agent runtime written in Go for self-hosted deployments. Its release binary embeds Hector Studio, a web UI served at the root path when hector serve runs. The runtime supports llm, sequential, parallel, loop, conditional, and remote agent types, using A2A for agent interoperability and MCP for tool connectivity. It persists sessions, tasks, and checkpoints in SQLite or PostgreSQL for recovery and queue handling. Teams can manage multi-tenant applications, authentication, triggers, RAG, guardrails, and notifications through YAML and the Admin API.
When started with hector serve, Hector serves Studio, the Admin API, and the agent runtime. It consumes YAML configuration or application configuration managed through /admin/apps, then executes llm, sequential, parallel, loop, conditional, or remote agents; LLM settings can target Anthropic, OpenAI, Gemini, or Ollama. Agents can call MCP tools over stdio or SSE, plus filetool, webtool, commandtool, memorytool, searchtool, todotool, approvaltool, and agenttool. Runtime events, tasks, checkpoints, and application configuration are persisted in SQLite or PostgreSQL; failed tasks can retry and be inspected or requeued through /admin/queue/dlq. It can also initiate or report work through cron triggers, webhooks, and A2A-compliant push notifications.
- A platform team needs to run an agent service on-premise, in an air-gapped network, or in its own cloud with a single binary and locally controlled credentials.
- A support platform needs to create isolated customer applications through the Admin API, with separate agent configuration, session storage, vector collections, and JWTs.
- An engineering team needs to expose existing MCP stdio or SSE services to agents while filtering the tools made available.
- An operations team needs daily reports on a cron schedule or needs to turn GitHub webhook payloads into agent inputs.
- A team running long-lived work needs SQL-backed retries, exponential backoff, checkpoints, recovery, and dead-letter-queue requeueing.
How do you install or deploy this agent?
On macOS or Linux, run: curl -fsSL https://gohector.dev/install.sh | sh, then: hector serve. Alternatives documented are Homebrew: brew install verikod/tap/hector followed by hector serve; or Docker: docker run -p 8080:8080 ghcr.io/verikod/hector:latest serve. On first launch, open http://localhost:8080/ and enter the admin secret printed in the terminal; Studio can then configure LLM providers, create agents, and start chatting. Cloud providers such as Anthropic and OpenAI need their respective API keys in configuration, for example ${ANTHROPIC_API_KEY} or ${OPENAI_API_KEY}. To build from source, run go build -o hector ./cmd/hector; the README specifies Go 1.24+.
How do you use this agent?
Start hector serve, enter the terminal-provided admin secret in Studio, configure an LLM provider, and create an agent; Studio includes streaming chat and a tool-call trace. Alternatively, define agents, tools, llms, guardrails, and document_stores in YAML, then run ./hector serve --config config.yaml. To enable the management interface, run hector serve --auth-secret "admin-secret" and POST to /admin/apps to create an application; the response includes an application JWT. Validate a deployment configuration with hector validate --config production.yaml before deployment.
What are this agent's strengths and limitations?
- The release build embeds Studio in a single Go binary described as roughly 30MB, with documented Linux, macOS, and Windows operation.
- It combines A2A-based agent interoperability with MCP tool connectivity, including both stdio and SSE transports.
- Sessions, tasks, and checkpoints persist in SQLite or PostgreSQL, with retries, exponential backoff, recovery, and dead-letter queue endpoints.
- Multi-tenant applications are managed through the Admin API with per-application JWTs, isolated state storage, and separate vector-store collections.
- Using cloud models from Anthropic, OpenAI, or Gemini requires the corresponding provider API keys; Ollama is the documented local alternative.
- A PostgreSQL deployment requires the operator to provide and operate PostgreSQL; SQLite is the documented default database.
- Building from source requires Go 1.24+; building a release binary with embedded Studio or running the Studio development server also requires Node.js.
- The supplied material does not document high-availability topology, backup procedures, resource sizing, or performance differences among vector stores and model providers.
How does this agent compare with similar options?
Provider selection is configuration-level: the examples list Anthropic, OpenAI, Gemini, and Ollama. Vector-store choices are chromem (the default), Qdrant, Pinecone, Weaviate, and Milvus; the supplied material does not establish performance or cost differences between them.
Key facts side by side with the most closely related agents.
| Agent | Source review | Form / cost | Stars | Updated | Language | Full support on |
|---|---|---|---|---|---|---|
| Hector Agent Runtime This agent | 65 · Some gaps | CLIFree + model costs | ★ 60 | 6mo ago | Go | OpenAI API · Claude API |
| EpicStaff Agent Workflow Platform | 78 · Good | Self-hosted service | ★ 358 | 5d ago | Python | — |
| AgenticOS Team Agent Workspace | 70 · Some gaps | Self-hosted serviceFree + model costs | ★ 242 | today | Python | OpenAI API · Claude API |
| CompozyOS | 60 · Some gaps | CLIFree + model costs | ★ 2.9k | today | Go | ChatGPT · Codex · Claude Code |
How does FollowAgents rate this agent?
Why each dimension lost points
The repository documents tool whitelists, command restrictions, approval controls, authentication, rate limits, PII redaction, and environment-based secrets, supporting ordinary least-privilege and sensitive-data controls. Approval is not required everywhere by default, and the docs show tenant deletion without a recovery path. Broad integrations and outbound notifications are described without a unified account of data flows and side effects. go.mod pins versions, but the packet shows no vulnerability review or dependency update policy. Attribution and maintenance responsibility are limited, and publisher identity remains unknown.
The README and installation, configuration, and troubleshooting guides cover common workflows, validation, retries, dead-letter queues, and error handling. However, the README repeats Quick Start content, and startup authentication defaults are described inconsistently across sections. CI workflows are present, but no run results are included, so actual runtime reliability cannot be inferred.
The documentation explicitly covers local development, production, multi-tenancy, cloud, and isolated environments, with choices across LLMs, storage, triggers, and orchestration. Tool permissions, trigger types, and deployment modes are configurable. Capability boundaries appear in feature lists and security advice, but limitations and scenario-specific fit are not fully documented.
Documentation is organized across installation, configuration, security, reference, and troubleshooting, with many examples and a clear MIT license. It explains installation options and the headless source-build limitation. Some material is duplicated or inconsistent, the supplied configuration reference is truncated, and release history, known limitations, and maintenance responsibility are not adequately described.
The product combines A2A/MCP, tool orchestration, persistence, an administration UI, and RAG in a configurable runtime; examples and operational guides support practical design and deployment. The value for common use cases is concrete, but operating it involves databases, secrets, external services, and security configuration. The packet does not quantify costs or fully explain the tradeoff between that complexity and the benefits.
Many configuration fields, CLI usages, and feature claims can be traced to examples, the reference guide, the CLI entry point, and CI files; multiple documents corroborate installation and configuration workflows. Some security, compliance, and protocol-compatibility statements remain README assertions without sufficient independent evidence or itemized verification in the packet. The docs do not consistently distinguish implemented facts from recommendations and product claims.
- The installation guide pipes a remote script into a shell or PowerShell; inspect the script source and verify authentication, network exposure, secrets, tool permissions, and data-deletion policies before deployment.
- Deleting an app removes its resources; the packet does not describe a recovery process.
Maintain this project? Add the FARS badge to your README
[](https://followagents.com/en/agents/hector)<a href="https://followagents.com/en/agents/hector"><img src="https://followagents.com/badge/hector.svg" alt="FARS review"></a>Recent releases
Latest entries from the project's GitHub Releases. Notes are quoted from upstream as written, not rewritten or tested by FollowAgents.
-
Release notes excerpt
Hector v1.41.2 Pure A2A-Native Declarative AI Agent Platform What's Changed Changelog * abe472b6deb12b3dbba290dbec44cd3be27e163d fixed agent tool calling/streaming Install macOS / Linux: ``` curl -fsSL https://gohector.dev/install.sh | sh ``` Windows (PowerShell): irm https://gohector.dev/install.ps1 | iex Homebrew: brew install verikod/tap/hector Docker: docker run -p 8080:8080 ghcr.io/verikod/hector:v1.41.2 serve Full Changelog: https://github.com/verikod/hector/compare/v1.41.1...v1.41.2View on GitHub ↗ -
Release notes excerpt
Hector v1.41.1 Pure A2A-Native Declarative AI Agent Platform What's Changed Changelog * 266bec76d19e70ddad1a406fbc35e6960103700a config foundation improvements Install macOS / Linux: ``` curl -fsSL https://gohector.dev/install.sh | sh ``` Windows (PowerShell): irm https://gohector.dev/install.ps1 | iex Homebrew: brew install verikod/tap/hector Docker: docker run -p 8080:8080 ghcr.io/verikod/hector:v1.41.1 serve Full Changelog: https://github.com/verikod/hector/compare/v1.41.0...v1.41.1View on GitHub ↗ -
Release notes excerpt
Hector v1.41.0 Pure A2A-Native Declarative AI Agent Platform What's Changed Changelog * 371ce8d477024d3b6914d8ebc2172b7a6c7a01c2 config foundation review Install macOS / Linux: ``` curl -fsSL https://gohector.dev/install.sh | sh ``` Windows (PowerShell): irm https://gohector.dev/install.ps1 | iex Homebrew: brew install verikod/tap/hector Docker: docker run -p 8080:8080 ghcr.io/verikod/hector:v1.41.0 serve Full Changelog: https://github.com/verikod/hector/compare/v1.40.3...v1.41.0View on GitHub ↗
FAQ
What are the license and model costs?
How is the management interface protected?
What happens after a task failure or restart?
Does it require a cloud LLM?
Can shell and filesystem access be constrained?
Thanks — we use this to improve the page.