Open source · Better together

Better together. Complete on their own.

Each system solves one problem end to end. Some pairs are designed to complement each other: one owns what the other deliberately leaves out. They connect only through public interfaces, so you can adopt one, both, or swap either for something else.

Optional by design

Four rules that keep every pairing optional.

Complementary products tend to drift into mutual dependency. These rules keep the benefit of combining them without making either one a prerequisite.

01

Each installs alone

No default install requires its partner. Every product is useful on its first day without the other.

02

Public interfaces only

Partners call each other's documented CLI or adapter contract. Neither reads the other's private files or state.

03

One owner per fact

Each piece of data or decision has exactly one home. Nothing is copied into the partner "just in case".

04

Degrade visibly

When a partner is missing or broken, the product falls back or reports degraded. It never silently substitutes or invents a result.

Holoself+Nextstep

Holoself + Nextstep

Who you are, and what you decided.

Available today

Holoself keeps your approved, reusable self: identity, voice, stories, and evidence. Nextstep keeps the record of one job search: opportunities, decisions, submissions, and outreach. Together, your agent drafts from your real evidence while every decision lands in an auditable record, and neither product holds the other's data.

How Holoself and Nextstep divide the work Holoself owns identity, voice, approved stories, evidence, and disclosure rules. Nextstep owns opportunities, decisions, submissions, outreach, and strategy experiments. Nextstep calls the holoself command-line tool with the self-only option to fill the self part of its context packet; if Holoself is not installed, a small native profile card is used instead. The coding agent receives one bounded packet combining both. Holoself YOUR SELF · REUSABLE • Identity and preferences • Voice and approved stories • Evidence and decisions • Disclosure and privacy rules Used by any AI tool, in any project Nextstep YOUR SEARCH · PROJECT-OWNED • Opportunities and decisions • Packages and submissions • Outreach and relationships • Strategy experiments Audited commands, in your data root holoself CLI · --self-only Nextstep asks; Holoself answers. No file access either way. Holoself not installed? Native profile card fills the gap Your agent gets one bounded context packet packet.self from Holoself (or the card) + opportunity context from Nextstep
Ownership never moves: Holoself doesn't store applications, and Nextstep doesn't copy your story bank.

Three ways to run it

Pick the one that fits. You can move between them later.

Standalone

Nextstep alone

  • The full job-search record: decisions, submissions, outreach, strategies.
  • A small native candidate-profile card supplies the essentials about you.
  • doctor reports healthy without Holoself.

Best if you want a trustworthy search record now. Explore Nextstep →

Standalone

Holoself alone

  • Approved context in any AI tool, through a career lens or any other.
  • Career projects keep their own research and notes.
  • Learning returns only as proposals you review.

Best if you want your context everywhere, not only in a job search. Explore Holoself →

Better together

Both

  • Drafts draw on your full, approved evidence rather than a summary card.
  • One source for who you are across the search and everything else you do.
  • The search record stays separate, auditable, and project-owned.

Connect with NEXTSTEP_HOLOSELF_HOME or a trusted HOLOSELF_EXECUTABLE.

When something is missing

The fallback rules, exactly as Nextstep applies them.

SituationWhat Nextstep does
Holoself is installed and answersUses Holoself for the self part of every context packet. A successful Holoself result always wins.
Holoself is not installedUses the native profile card. Nothing else changes.
Holoself is installed but failsLeaves the self context empty and reports degraded. It does not silently fall back to the card, so a broken setup is never hidden.
You prefer the native cardSet the source preference to native, and Holoself is never called.

Source: the candidate-profile rules in the Nextstep CLI reference ↗.

AgentFlow SDLC+Meshloop

AgentFlow + Meshloop

Who decides, and who executes.

Integration in development

AgentFlow governs delivery: approved intent, handovers, evidence, and acceptance. Meshloop executes engineering work: task graphs, isolated worktrees, checks, and repair. Paired through an optional provider adapter, AgentFlow can hand a scoped build to Meshloop and judge what comes back, while Meshloop's "pass" is never the final word.

How AgentFlow and Meshloop divide the work AgentFlow's delivery lane runs frame, hand over, build, check, and accept. The build step can be delegated through an optional provider adapter to Meshloop, which plans a task graph, runs isolated worktrees, runs checks, and repairs, then returns a technical receipt with digest-verified artifacts. AgentFlow checks that evidence and alone decides acceptance. AgentFlow SDLC GOVERNS · DECIDES Frame Hand over Builddelegated Check evidence Accept Optional provider adapter · public interface only Meshloop EXECUTES · VERIFIES TECHNICALLY Plan task graph Isolated worktrees Checks + repair Technical receiptnot acceptance approved scope + limits receipt + SHA-256 artifacts
The dashed Build step is the only point of delegation. Scope flows down, evidence flows up, and acceptance stays with AgentFlow.

Three ways to run it

Both products work today on their own. The pairing is being qualified.

Standalone

AgentFlow alone

  • Roles, handovers, deterministic gates, and acceptance for AI-assisted delivery.
  • Executes through Claude Code, Codex, Agy, Pi, Grok, or an explicit manual path.
  • No Meshloop, collector, or other product required.

Best when you need accountable delivery with the tools you have. Explore AgentFlow →

Standalone

Meshloop alone

  • Its own human gates: review the plan, accept, then integrate.
  • Runs from the CLI, slash commands, or MCP without any AgentFlow configuration.
  • Isolated worktrees and compiler-verified repair on day one.

Best when you want parallel agents with safe isolation now. Explore Meshloop →

Better together · preview

Both

  • AgentFlow's accountability around Meshloop's parallel execution.
  • Meshloop works inside an approved scope and narrowed limits it cannot widen.
  • Evidence returns digest-verified and bound to the tested candidate.

An optional Meshloop provider is on AgentFlow's development branch. It is not in a release yet.

Guarantees designed into the boundary

From AgentFlow's engineering-provider profile, which is proposed and still under qualification.

  • Scope can't growMeshloop's task graph can refine the approved scope but never enlarge it.
  • A pass is not acceptanceA technical receipt is evidence. AgentFlow validates it independently before accepting.
  • Unknown stays unknownA timeout or lost reply is reconciled, never recorded as a fabricated pass.
  • Mismatch fails earlyAn unsupported version or capability blocks before any work is dispatched.
  • No shared internalsAgentFlow never reads Meshloop's database; Meshloop never imports AgentFlow's contracts.
  • Independent upgradesEach product upgrades on its own within a tested compatibility matrix.

Source: engineering-provider profile ↗ and ADR 012 ↗, both on the development branch.