@yuanhao: Riding the trend of graph engineering, actually yoyo has quietly evolved into a durable states graph harness a few weeks ago, which is the persistent state mentioned in my previous long article. Interested can check the GASP protocol…

X AI KOLs Timeline Tools

Summary

The yoyo framework achieves persistent directed graph state management by integrating the GASP (Git Agent State Protocol), enabling agent states to be branchable, versionable, auditable, and replayable, marking a shift from wild growth to traceable persistence.

Riding the trend of graph engineering, actually yoyo has quietly evolved into a durable states graph harness a few weeks ago, which is the persistent state mentioned in my previous long article. If interested, check out the GASP protocol (Git / Graph Agent State Protocol), turning your agent's "black box loop" into a green version, branchable, versionable, auditable, and replayable. Leaving a placeholder: if you are interested in how yoyo, by integrating the GASP protocol, evolved from wild growth to support traceable and backtrackable persistent states, I might summarize it another day. I am also interested in how intelligent agents can be deployed in enterprises for production, and discussions are welcome. GASP Spec: https://gasp.yolog.dev
Original Article
View Cached Full Text

Cached at: 07/21/26, 01:37 AM

To ride the wave of graph engineering, yoyo actually quietly evolved into the durable states graph harness a few weeks ago — the persistent state I mentioned in my previous long post.

If you’re interested, check out the GASP protocol (Git / Graph Agent State Protocol), which turns your agent’s “black-box loop” into a green version — branchable, versionable, auditable, replayable.

Digging a hole: If you’re curious about how yoyo, by integrating the GASP protocol, evolved from a wild growth state into a persistent state that supports traceability and backtracking, I’ll summarize it another day. Making intelligent agents production-ready in enterprises is also one of my interests — feel free to discuss.

GASP Spec:https://gasp.yolog.dev


GASP — The repo is the agent.

Source: https://gasp.yolog.dev/ Git Agent State Protocol · status: buildable

GASP is a git-native standard for portable agent state. An append-only event log folds into a typed graph of goals, patches, evals, and decisions — point any conformant runtime at the repo URL and the same agent resumes anywhere, on any model.

$cargo run -q -- fixture --fixture# verify the fixture, all 7 checks

01 — THE PROBLEM

Agent state today is trapped

Swapping models means amnesia — because the state was never yours to begin with.

Transcripts rot in vendor folders

Session logs pile up in undocumented formats you don’t own and can’t parse tomorrow.

Memory dies with the runtime

Identity, skills, and learnings live inside one harness. Switch tools and the agent forgets who it is.

Nothing explains why

No lineage from goal to change to test to decision — just a flat transcript of what happened.

02 — HOW IT WORKS

The log folds into a graph

One run from the spec’s worked example: a skill patch is proposed, tested, and promoted. Domain events record thewhy; eachstate\.ops\_appliedevent folds into the graph.

state/events.jsonlappend-only · source of truth

folded graphqueryable · regenerable

APPEND

Every semantic moment is one JSONL line — goals, runs, tool calls, evals, decisions.

{“kind”:“eval.finished”,“payload”:{“status”:“Passed”},...}

FOLD

The log folds into a typed graph along the causal spine.

goal → patch → eval → decision → promotion

SHIP

Git commits it, git ships it. The same agent resumes anywhere.

restore = clone + replay

03 — THE MODEL

One repo, two media

An agent has an executor and its state. GASP governs only state — swap the executor freely. Events reference git artifacts; git stores them. Neither duplicates the other.

git owns the concretewhat

Code,identity/,skills/, commits, diffs.

losslessbisectableshippable

the log owns the semanticwhy

Typed events — goals, runs, failures, patches, evals, decisions — committed atstate/events\.jsonl.

what it was trying to dowhy each change existswhat was decided

THE CAUSAL SPINE — a backbone, not a forced workflow

goal→task→run→observation→failure→hypothesis→patch→eval→decision→promotion

04 — CONFORMANCE

Conformance is a test, not a claim

Five rules, seven mechanical checks, one canonical fixture. Satisfy them and any other conformant runtime can resume your agent — that is what makes GASP a standard and not an API.

1

State lives in a git repo

At the standard layout — log, identity, skills, projections.

2

The event log is append-only

Committed, and using the shared event vocabulary.

3

Identity & skills are artifacts

Committed, loaded at runtime, never compiled in.

4

Restore is clone + replay

Fold the committed log into state; load identity and skills.

5

The executor is swappable

Swapping model or runtime touches\.agent/config\.toml, nothing else.

verified mechanically

The conformance kit runs 7 checks against any emitted repo — including replay and the pairing rule.

$conformance-check agent-repo/

[PASS]check 1 — envelope round-trip

[PASS]check 2 — replay

[PASS]check 3 — vocabulary

[PASS]check 4 — append-only in git

[PASS]check 5 — causation integrity

[PASS]check 6 — restore

[PASS]check 7 — domain↔ops consistency

conformant: all checks passed

05 — REPO LAYOUT

Four tiers, not two

Everything in the agent-repo belongs to a tier that says how it may change.

First-class, committed.The log, identity, skills. Append-only; identity is human-gated.

Derived, append-only.Distilled facts — never a history mirror.

Projections, regenerable.Active memory, journal, snapshots. Free to overwrite.

Cold, prunable.Raw transcripts. Never the source of truth.

agent-repo/

├── AGENT.mdmanifest

├── identity/human-gated constitution

├── skills/versioned capabilities

├── state/events.jsonlsource of truth

├── memory/facts.jsonldistilled facts

├── memory/active_memory.mdsynthesis

├── journal/narrative projection

├── transcripts/cold archive

├── snapshots/fast-restore checkpoints

└── .agent/config.tomlexecutor binding

06 — PROOF

yoyo, the octopus agent

yoyo lives here

yoyo, a self-evolving agent with 100k+ lines of self-written Rust, keeps its identity, skills, memory, and lineage in a GASP repo — recording every evolve, skill, and social session since Day 125. Its state repo passes all 7 checks.

“Cloneyoyo-gaspand yoyo wakes up knowing who it is.”

yoagentexecutes.

yoagent-stateremembers.

yoyo evolveimproves.

gitships.

07 — ECOSYSTEM

The ecosystem

$cargo run -q -- fixture --fixture# verify the fixture

$cargo run -q -- path/to/agent-repo# verify any repo

$cargo test# kit self-tests

Similar Articles

@yuanhao: https://x.com/yuanhao/status/2066341005847142674

X AI KOLs Timeline

Yoyo is an AI agent that self-evolves every 8 hours on GitHub Actions. Its key to success lies in a harness design of a stateless agent plus persistent state (git repository). The article deeply analyzes simple solutions to issues such as memory, context, feedback, verification, etc., emphasizing that persistent state is more critical than the model itself.

@ludamn513: https://x.com/ludamn513/status/2108809228978880988

X AI KOLs Timeline

Using Pi Durable as a starting point, the article breaks down the evolution of the Agent Harness architecture: decoupling the persistence system, agent loop, and execution environment to enable lossless state recovery, codemode tool calls, and server/client separation. It also proposes a scalable architecture for a long-running Harness, with the goal of reducing hardware resource consumption by an order of magnitude.

@JoshARosen: https://x.com/JoshARosen/status/2107840212915077350

X AI KOLs Following

一篇架构对比文章,分析 Pi Durable 与 OpenCode 的设计差异:Pi Durable 将模型生成、工具调用等序列化为可调度的持久任务,使工作不再绑定于单个进程,而传统会话式 harness(如 OpenCode、Claude Code、Codex)仍依赖进程内的活动 agent 循环。

@Xudong07452910: This latest paper, Scaling Laws for Agent Harnesses, is a must-read for those working on Agent Harnesses. It highlights a key point: Agents don't necessarily become stronger by running more tokens, tuning more tools, or looping more rounds. What really matters is that these...

X AI KOLs Timeline

This paper proposes Effective Feedback Compute (EFC) as a scaling coordinate for measuring Agent Harness performance, emphasizing that effective feedback is more important than raw compute, with important implications for Agent system design.