OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Agent Frameworks

Trpc Agent Go

A Go framework for building production agent systems with graph workflows, LLM agents, tools, memory, knowledge retrieval, evaluation and observability.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Trpc Agent Go — OpenViST project profile in Agent Frameworks.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it for Go-based agent services that need orchestration, state, tools, retrieval or production-oriented evaluation and observability rather than only a basic model interaction.

Who it is for

  • Go developers building AI agent applications
  • Teams coordinating multiple agents and workflow stages
  • Engineers integrating agents with A2A, AG-UI or MCP services
  • Developers needing evaluation and OpenTelemetry-based observability

Documented uses

  • Build graph-based agent workflows
  • Coordinate chained, parallel or cyclical agents
  • Add function, MCP, web-search, code-execution or custom-service tools
  • Manage session, memory, artifacts and knowledge retrieval
  • Evaluate agent quality and instrument runtime behavior
Before you choose

Requirements & limits

The repository is public, described as open source and identified with an Apache-2.0 license. Documented platforms include Linux, Windows, macOS, server and self-hosted environments.

  • Go is the primary implementation language and the framework is designed around Go service patterns.
  • Graph workflows support conditional routing and multi-agent coordination.
  • The stack includes session and memory state, knowledge retrieval, evaluation and OpenTelemetry observability.
  • Protocol integration spans A2A, AG-UI and MCP.
  • The repository documentation includes skill loading and execution, so code-execution behavior should be reviewed when enabling those capabilities.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Set up a Go agent with persistent memory and tools

Create an agent configuration that can use memory tools and retain context through a runner.

Before you start

  • A Go project using the Trpc Agent Go framework.
  • A model configured for the LLM agent.
  • The documented in-memory service and runner components.

Steps

  1. Create an in-memory memory service.

  2. Expose the service's tools to an LLM agent.

  3. Attach the memory service to a runner.

  4. Run the agent with user and session identifiers so context can be associated across sessions.

Expected outcome

An agent configuration with memory tools and runner-level memory state.

Documentation 1 ↗
COMPARE OPTIONS

Compare options for Agent orchestration

These projects document a common task and share a project role. This is a source-based comparison, not an execution benchmark or a guarantee of interchangeability.

ProjectDocumented purposePlatformAccess and requirements
Trpc Agent GoBuild graph-based agent workflowsLinux, macOS, Self-hosted, ServerThe repository is public, described as open source and identified with an Apache-2.0 license. Documented platforms include Linux, Windows, macOS, server and self-hosted environments.
AgeniteDefine typed tools with JSON Schema validation and error handling.CLI
VeldraCreate an agent with a policy, tools, skills, knowledge base and reasoning method.Self-hostedThe documented deployment is self-hosted and uses a sign-in gate after a first-run administrator account is created.
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
1 October 2026
Original website title
trpc-group/trpc-agent-go · Official homepage title · retained in its source language
How we review sourcesSuggest a correction