Skip to content

Entry

Effective Harnesses for Long-Running Agents

Appears in 5 awesome lists

Anthropic's pattern for maintaining agent progress across multiple context windows: an initializer agent sets up the environment once and hands off to a coding agent that makes incremental progress each session. The structured handoff mechanism — feature lists, git commits, and test gates as…

Open anthropic.com

Found in these lists

Awesome Artificial Intelligence

Section: Durable and asynchronous agents · Patterns for agents that make progress across multiple context windows and recover from failure.

ActiveScore 85

Awesome Harness Engineering

Section: Planning & Task Decomposition · Anthropic's pattern for maintaining agent progress across multiple context windows: an initializer agent sets up the environment once and hands off to a coding agent that makes incremental progress each session. The structured handoff mechanism — feature lists, git commits, and test gates as…

FreshScore 93

Awesome Prompts

Section: Harness Engineering · Long-running agent design

FreshScore 96

Best Of Agent Harnesses

Section: Related Resources · Session bridging, feature lists, incremental progress, testing

FreshScore 80

Awesome Harness Engineering

Section: Foundations · Anthropic's core article on initializer agents, feature lists, init.sh, self-verification, and handoff artifacts across many context windows.

FreshScore 93

deepagents

LangChain's batteries-included agent harness (released April 2026) with built-in planning, filesystem tools, shell access, sub-agents, and auto-summarization. The clearest open-source demonstration of how a general-purpose coding agent harness can be made ready-to-run out of the box while…

In 8 listsDetails

ECC

Affaan Momin's agent-harness operating system: 68 specialized agents, 286 skills, hooks, memory, continuous learning, and AgentShield security scanning across Claude Code, Codex, Cursor, OpenCode, and other harnesses. The clearest open-source example of packaging an end-to-end engineering workflow…

In 7 listsDetails

Orca

The AI orchestrator for running Codex, Claude Code, OpenCode, and Pi side-by-side in isolated git worktrees. It turns fleet-of-agents execution into a polished desktop IDE with a mobile companion, making parallel agent harness design accessible beyond shell-scripting teams.

In 5 listsDetails

Better Harness

Evaluates coding-agent workflows across five dimensions and turns project and session evidence into prioritized, evidence-bounded findings with scoped repair actions. Runs inside Claude Code, Codex, Cursor, GitHub Copilot, and other hosts, making it a practical cross-tool diagnostic layer for…

In 4 listsDetails

GitHub Spec Kit

GitHub's open-source toolkit for spec-driven development: spec.md → plan.md → tasks.md artifacts convert natural-language intent into a machine-checkable plan before any code is written, with /specify, /plan, /tasks, and /implement commands that run across Claude Code, Copilot, Codex, and Gemini…

In 4 listsDetails

The Anatomy of an Agent Harness

LangChain's structural breakdown of the five primitives that compose a harness: filesystem (durable state + agent collaboration surface), code execution (autonomous problem-solving without pre-designed solutions), sandbox (isolation + verification), memory (cross-session persistence), and context…

In 3 lists

Skill Issue: Harness Engineering for Coding Agents

Practitioners' guide covering all harness configuration points for coding agents: system prompts, MCP tool selection, skills for progressive disclosure, sub-agents as context firewalls, hooks for deterministic control, and back-pressure verification. The central argument — that most agent failures…

In 3 lists

Mirage

Swaps the filesystem and bash providers for a mirage virtual workspace: file tools and shell commands run over mounted resources (RAM, S3, Redis, Slack, Gmail, Notion, Postgres) instead of the host disk, with per-mount read/write/exec modes, per-command sandbox routing (monty, pyodide, quickjs in…

In 3 lists