Agent Atlas / Agent frameworks

NousResearch/hermes-agent

A local agent framework whose approvals, worker threads, undo paths, terminal UI, telemetry, and computer-use tools expose the cost of turning broad capability into governable work.

Agent framework Scope profile Reported + sourced Reviewed July 21, 2026
Intended operator

Developers and operators running a local general-purpose agent.

Primary surfaces

terminal agent / tools and plugins / delegated workers

Tracked repository

NousResearch/hermes-agent

Teaching mechanism

Approval state follows the worker thread

Thread-local approval state narrows the risk that consent for one task becomes ambient authority for another.

Evidence limitThread-local state does not prove that every executor or plugin consumes it correctly.
Inspect the source
System map status

Reporting is still in progress.

This scope profile names the project's place in the field and one useful mechanism. It does not claim that every runtime boundary has been inspected.

Learn Through This Project

8 lessons
Chapter 1 Before the First Model Request Chapter 3 Tool Calls: Contract, Authorization, Execution Chapter 4 Loops, Workflows, and Recovery Chapter 5 Delegation Is a Distributed System Chapter 7 The Approval Trap Chapter 8 The Human Control Loop Chapter 9 Trust Must Make Its Case Chapter 10 The Future Has Three Branches

Compare Its Boundaries

7 labs
Comparison labTool ContractsComparison labDelegation ReceiptsComparison labApproval BoundariesComparison labHuman WorkbenchComparison labSessions And RecoveryComparison labEvidence And EvaluationComparison labMaturity Signals

Latest Reporting

8 articles
API Discovery: Tail a Delegated Hermes Agent at Work

July 20, 2026 — Hermes' public delegate_task surface can now return a live, local log for each child—useful when a background fan-out needs observation without flooding the parent conversation. NousResearch/hermes-agent

 Codex Stops Asking Its Subagents the Same Question Twice

July 20, 2026 — A Codex TUI patch cuts duplicate status reads by treating new, resumed, and actively streaming agent threads as different lifecycle states. openai/codex, NousResearch/hermes-agent

 A Computer-Use Agent Needs a Second Meaning of Success

July 19, 2026 — Hermes now tells a desktop-driving agent whether an input merely reached a driver or was actually confirmed to have changed the interface—and it makes foreground escalation a separate decision. NousResearch/hermes-agent

 Background Agent Work Needs a Receipt

July 15, 2026 — Hermes and OpenClaw are fixing different failure windows in the same promise: delegated work has to arrive somewhere a person can use it. NousResearch/hermes-agent, openclaw/openclaw

 Hermes Turns Health Checks Into a Runtime Contract

July 12, 2026 — A new authenticated readiness endpoint checks the parts of an agent gateway that can make it unreliable—without reading payloads, leaking configuration, or trying to repair anything. NousResearch/hermes-agent

 Agent Runtimes Move Trust To The Exit Gate

July 9, 2026 — OpenClaw, Codex, and Hermes all changed runtime trust surfaces this week, making the last moment before a tool call, secret handoff, or approval the place operators need to inspect. openai/codex, openclaw/openclaw, NousResearch/hermes-agent

 Harness Engineering Is Becoming The Field's Self-Improvement Layer

July 8, 2026 — Lilian Weng's July 4 map of self-improving harnesses gives builders a constructive middle path: improve the runtime around the model, but keep evidence, permissions, and evaluation legible enough that the loop can be trusted. lilianweng/lilianweng.github.io, openai/codex, different-ai/openwork, openclaw/openclaw, NousResearch/hermes-agent, earendil-works/pi, anomalyco/opencode

 Self-Evolving Agents Need Receipts For The Loop

July 8, 2026 — Shilong Liu's taxonomy widens the self-improvement story beyond harnesses: agents may optimize artifacts, modify the harness, or learn in the model, but each loop needs evidence about what changed and what stayed outside the optimizer. NousResearch/hermes-agent openai/codex openclaw/openclaw different-ai/openwork anomalyco/opencode

Primary Sources

Hermes Agent repository

Primary runtime and tool source.

Open Questions

  • Can a delegated worker prove the exact authority, result, and live status it inherited?

Evidence state describes what this Atlas profile can support today. It is not a product score and it is not evidence that uninspected capabilities are absent.