AgentIndex icon
AgentIndex
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Submit Tool
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompare
Home/
Multi-Agent/
nac
nac logo

nac

Active·★ 284·Apache-2.0·Updated 2026-10-22

nac is an open-source agent harness designed for managing ambitious, long-running tasks like experiments, training, and infrastructure. It employs a thread-and-episode architecture where a central orchestrator plans work, launches threads, and receives structured summaries of accomplishments.

nac sits in the Multi-Agent category, so it is usually better judged by workflow fit, deployment style, and team needs than by isolated features alone. Based on the available metadata, it leans most clearly toward Agent Harness for long-running, ambitious tasks. A representative use case is Managing and orchestrating long-running experimental tasks. The listed license is Apache-2.0. GitHub stars are currently 284. Relevant tags include AI Agent, Orchestration.

This write-up is based on the project's README and public repository data. We have not hand-tested the tool.

© 2026 AgentIndex.app|Built by a 10-year iOS Developer.
Best by use caseAboutContactAdvertisePrivacy PolicyTerms of UseQYSGitHubBuy me a coffee ☕

Browse by Category

MCP ServersCode AssistantWorkflow AutomationRAG / Knowledge BaseMulti-AgentBrowser AutomationLLM InfraDev ToolingObservability

Not affiliated with Anthropic, OpenAI or Microsoft.

Guides
#AI Agent
#Orchestration
#Task Management
#Multi-agent Systems
#LLM Tooling
#Prototyping
#Agent Harness
$ Install
$ curl -fsSL https://raw.githubusercontent.com/arcee-ai/nac/main/scripts/install.sh | sh
↗ Visit site★ GitHub
01

Features

01Agent Harness for long-running, ambitious tasks
02Thread-and-Episode Architecture for task decomposition
03Central Orchestrator for planning and thread launching
04Structured Summaries (Episodes) of completed work
05Flexible Model Provider Authentication (Arcee, OpenAI, etc.)
02

Why choose it

+Agent Harness for long-running, ambitious tasks
+Thread-and-Episode Architecture for task decomposition
+Managing and orchestrating long-running experimental tasks
+Supports 3 platforms or runtime environments.
03

Trade-offs

!The final decision should still be made through side-by-side comparison with similar tools.
04

Compatibility

Linux/macOS
OS
Verified via docs
Web Browser
Interface
Verified via docs
LLM APIs
Model Provider
Verified via docs
05

Quick start

1
$ curl -fsSL https://raw.githubusercontent.com/arcee-ai/nac/main/scripts/install.sh | sh
06

Use cases

↳Managing and orchestrating long-running experimental tasks
↳Automating and supervising AI model training runs
↳Streamlining infrastructure management and deployment
↳Accelerating prototyping and development cycles
07

Alternatives

⚡Top VS:
VSforge-orchestrator★162→VSCrewAI★60.0k→VSoh-my-dag★44→VS

Comments

Log in to leave a comment

No comments yet. Be the first!

On this page
01Features02Why choose it03Trade-offs04Compatibility05Quick start06Use cases
AI-company
★373
→
forge-orchestrator logo
forge-orchestrator★ 162
NXTG-Forge orchestrator: multi-AI task orchestration with file locking, knowledge capture and drift detection. Rust. Public preview (source-available, FSL-1.1-ALv2).
VSCompare→
CrewAI logo
CrewAI★ 60.0k
Framework for orchestrating role-playing, autonomous AI agents. By working together, your Crew can tackle complex tasks.
VSCompare→
oh-my-dag logo
oh-my-dag★ 44
The orchestration layer under your coding agent. Turns work into a typed graph, runs one model per node, and takes the verdict from outside the model — exit codes, write-set checks, and a cross-family verifier. MCP server, 50 tools, bring your own models.
VSCompare→
AI-company logo
AI-company★ 373
Multi-agent team operating system for Claude Code. 108 MCP tools, 40+ agent templates, 10 lifecycle hooks, 7 pipeline workflows. Persistent teams, structured meetings, task wall, real-time React dashboard. No LangChain/AutoGen — pure CC native integration.
VSCompare→
Hexis logo
Hexis★ 118
Centrally manage AI-agent skills, tools, context, permissions, and identity across your entire org. Self-hosted, Git-backed and MCP-native.
VSCompare→
omk logo
omk★ 148
Evidence-gated runner for Codex, Claude Code, OpenCode, and local coding agents. Routes tasks into scoped DAG lanes with replayable artifacts.
VSCompare→
itasca-mcp logo
itasca-mcp★ 219
MCP server connecting AI agents to ITASCA engines (PFC, FLAC, 3DEC, MPoint, MassFlow) — run numerical simulations through natural conversation
VSCompare→
dos-kernel logo
dos-kernel★ 20
Catch your AI agents when they lie about what they shipped — verifies claims against git instead of believing the agent.
VSCompare→
See all alternatives →
07
Alternatives
arcee-ai /
nac
↗

Give AI agents ambitious work without losing the plot. nac is an open-source harness for long-running tasks, using a central orchestrator, threads, and structured episodes to stay aligned with your intent.

284Apache-2.0
Last commit1d ago
StatusActive
CategoryMulti-Agent
Links
Documentation↗Discussion↗Issues↗Releases↗
Cloud Infrastructure
Ad

Deploy on DigitalOcean

Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.

Claim $200 Free Credit