I already see the agent’s steps in Cursor or a README. Why Nika?

Seeing the steps is not the same as enforcing the procedure. A README is documentation; a Nika file is an executable contract: versionable, replayable, permission-bound, auditable, and portable off any platform. You do not just read what it intends to do; the runtime holds it to exactly that.

Isn’t this just YAML, or another workflow engine?

The syntax is plain YAML, but the point is not the syntax. The point is the reviewable, enforced plan. The 4 verbs (infer · exec · invoke · agent) are native execution models, each one explicit and typed, with a permits: block the runtime enforces before anything runs. The file is the control surface, not the formatting.

Why not LangGraph, n8n, or MCP (agent tools)?

They live at a different layer. Frameworks help you orchestrate and assistants help an agent act; MCP exposes tools to call. Nika is the contract-and-control layer underneath: it makes the plan reviewable and enforceable, and it runs their tools through invoke, allow-listed and traced. It complements them rather than replacing them.

Does my data leave my machine?

Local-first, any model: fully local, or any API. Run a local model and nothing leaves at all. Every plan declares its network egress in its permits: block, and it is default-deny: omit the hosts and the workflow physically cannot reach the network. The file states exactly what can leave, and the runtime enforces it. 5 of the 17 providers are local.

Is it production-ready? What’s the license?

Honest answer: Nika is early. Real semver toward a 1.0 launch, currently at v0.105.0, shipping in the open. It is one Rust binary you can install and run today. The engine is AGPL-3.0-or-later; the spec is Apache-2.0. We would rather you trust the spec and the binary than a maturity claim we have not earned yet.

{"t2-invoice-chaser":"nika: v1\nworkflow:\n  id: invoice-chaser\n  description: \"Ledger CSV → overdue filter → drafted reminders → human gate → drafts file\"\n\nmodel: ollama/qwen3.5:4b   # local · zero key · swap for groq/llama-3.3-70b (drafting is a fast-model job)\n\nvars:\n  ledger_csv: \"./finance/invoices.csv\"\n\ntasks:\n  ledger:\n    invoke:\n      tool: \"nika:read\"\n      args: { path: \"${{ vars.ledger_csv }}\" }\n\n  rows:\n    with:\n      csv: ${{ tasks.ledger.output }}\n    invoke:\n      tool: \"nika:convert\"\n      args:\n        input: \"${{ with.csv }}\"\n        from: csv\n        to: json\n        has_header: true\n\n  overdue:\n    with:\n      rows: ${{ tasks.rows.output }}\n    invoke:\n      tool: \"nika:jq\"\n      args:\n        input: \"${{ with.rows }}\"\n        expression: 'map(select(.status == \"overdue\"))'\n\n  drafts:\n    with:\n      overdue: ${{ tasks.overdue.output }}\n    when: ${{ size(with.overdue) > 0 }}\n    infer:\n      prompt: |\n        Draft one short, polite payment reminder per overdue invoice ·\n        ${{ with.overdue }}\n        Markdown · one section per client · firm but warm.\n\n  approve:\n    with:\n      drafts: ${{ tasks.drafts.output }}\n    when: ${{ with.drafts != null }}   # nothing drafted · nothing to approve\n    invoke:\n      tool: \"nika:prompt\"\n      args:\n        message: \"Save the reminder drafts for sending?\"\n        default: false\n\n  save:\n    with:\n      drafts: ${{ tasks.drafts.output }}\n      approved: ${{ tasks.approve.output }}\n    when: ${{ with.drafts != null && with.approved == true }}   # zero overdue → drafts skipped (null) · don't write nothing\n    invoke:\n      tool: \"nika:write\"\n      args:\n        path: \"./finance/reminders-to-send.md\"\n        content: \"${{ with.drafts }}\"\n\noutputs:\n  overdue:\n    value: ${{ tasks.overdue.output }}\n    description: \"The overdue rows the reminders were drafted for\"\n","t4-deep-research-brief":"nika: v1\nworkflow:\n  id: deep-research-brief\n  description: \"plan → budgeted research agent → thinking synthesis → brief on disk\"\n\nmodel: ollama/qwen3.5:4b   # local default · per-task overrides below pick stronger models\n\nvars:\n  topic:\n    type: string\n    required: true\n    description: \"What to research\"\n\ntasks:\n  plan:\n    infer:\n      model: anthropic/claude-haiku-4-5    # planning is a fast-model job\n      prompt: \"Break '${{ vars.topic }}' into 4 sharp research queries · no overlap.\"\n      schema:\n        type: object\n        required: [queries]\n        properties:\n          queries:\n            type: array\n            items: { type: string }\n\n  investigate:\n    with:\n      plan_queries: ${{ tasks.plan.output.queries }}\n    agent:\n      system: |\n        You are a rigorous researcher. Work the queries one by one ·\n        fetch sources · keep verbatim quotes · note what each source\n        actually supports. Call nika:done when the plan is exhausted.\n      prompt: \"Research plan · ${{ with.plan_queries }}\"\n      tools:\n        - \"nika:fetch\"                 # the web\n        - \"nika:write\"                 # scratch notes\n        - \"nika:done\"                  # the loop-completion sentinel\n      max_turns: 25\n      max_tokens_total: 150000\n      schema:\n        type: object\n        required: [findings, sources]\n        properties:\n          findings:\n            type: array\n            items: { type: string }\n          sources:\n            type: array\n            items: { type: string }\n\n  brief:\n    with:\n      investigate_findings: ${{ tasks.investigate.output.findings }}\n      investigate_sources: ${{ tasks.investigate.output.sources }}\n    infer:\n      prompt: |\n        Findings · ${{ with.investigate_findings }}\n        Sources · ${{ with.investigate_sources }}\n        Write the executive brief · what's true · what's contested ·\n        what it means · what to do. Two pages max.\n      thinking:\n        enabled: true\n        budget_tokens: 8000\n\n  save:\n    with:\n      brief: ${{ tasks.brief.output }}\n    invoke:\n      tool: \"nika:write\"\n      args:\n        path: \"./research/${{ vars.topic }}.md\"\n        content: \"${{ with.brief }}\"\n        create_dirs: true\n\noutputs:\n  brief: ${{ tasks.brief.output }}\n  sources:\n    value: ${{ tasks.investigate.output.sources }}\n    description: \"Every source the agent actually used\"\n","t3-localization-factory":"nika: v1\nworkflow:\n  id: localization-factory\n  description: \"glob docs → parallel read → parallel translate → mirror tree\"\n\nmodel: ollama/qwen3.5:4b   # local default · swap for mistral/mistral-large (EU model for EU locales)\n\nvars:\n  lang: \"fr\"\n  source_glob: \"./docs/**/*.md\"\n\ntasks:\n  files:\n    invoke:\n      tool: \"nika:glob\"\n      args:\n        pattern: \"${{ vars.source_glob }}\"\n        exclude: [\"**/node_modules/**\"]\n\n  texts:\n    with:\n      files: ${{ tasks.files.output }}\n    for_each: ${{ with.files }}\n    max_parallel: 8\n    invoke:\n      tool: \"nika:read\"\n      args: { path: \"${{ item }}\" }\n\n  pairs:\n    with:\n      files: ${{ tasks.files.output }}\n      texts: ${{ tasks.texts.output }}\n    invoke:\n      tool: \"nika:jq\"\n      args:\n        input: [\"${{ with.files }}\", \"${{ with.texts }}\"]\n        expression: \"transpose | map({path: .[0], text: .[1]})\"\n\n  translated:\n    with:\n      pairs: ${{ tasks.pairs.output }}\n    for_each: ${{ with.pairs }}\n    max_parallel: 3                    # rate-limit the provider\n    fail_fast: false                   # finish the batch · a failed file yields null at its index\n    on_error:\n      recover: null                    # null keeps the transpose zip aligned (order preserved)\n    infer:\n      prompt: |\n        Translate to ${{ vars.lang }} · keep markdown structure, code blocks\n        untouched, and the original tone ·\n        ${{ item.text }}\n\n  bundle:\n    with:\n      pairs: ${{ tasks.pairs.output }}\n      translated: ${{ tasks.translated.output }}\n    invoke:\n      tool: \"nika:jq\"\n      args:\n        input: [\"${{ with.pairs }}\", \"${{ with.translated }}\"]\n        expression: \"transpose | map(select(.[1] != null)) | map({path: .[0].path, text: .[1]})\"\n\n  mirror:\n    with:\n      bundle: ${{ tasks.bundle.output }}\n    for_each: ${{ with.bundle }}\n    max_parallel: 8\n    invoke:\n      tool: \"nika:write\"\n      args:\n        path: \"./i18n/${{ vars.lang }}/${{ item.path }}\"\n        content: \"${{ item.text }}\"\n        create_dirs: true\n\noutputs:\n  files:\n    value: ${{ tasks.files.output }}\n    description: \"Every source file that was mirrored\"\n"}

[ INTENT AS CODE ]

Useful AI work shouldn’t disappear into chats.

Nika turns repeatable AI work into files you can run, review, diff and share: audited before a token is spent, with a verifiable receipt after every run. An agent writes the plan; you review it; the runtime enforces it.

Repeatable AI work as a file: audited before a token is spent, a receipt after every run. The runtime enforces it.

See it runtry it in your browseror in VS Code / Cursor

v0.105.0macOS · LinuxAGPL-3.0

see it run

1nika: v12workflow:3  id: daily-brief4# local model · your notes never leave5model: ollama/llama3.2:3b67# the file IS the blast radius8permits:9  fs: { read: [ ./notes/* ], write: [ ./brief.md ] }10  tools: [ "nika:read", "nika:write" ]1112tasks:13  notes: { ◆invoke: { tool: "nika:read", args: { path: ./notes/today.md } } }14  inbox: { ◆invoke: { tool: "nika:read", args: { path: ./notes/inbox.md } } }15  calendar: { ◆invoke: { tool: "nika:read", args: { path: ./notes/calendar.md } } }1617  triage:18    with:19      inbox: ${{ tasks.inbox.output }}20    ◇infer: { prompt: "Flag what is urgent: ${{ with.inbox }}", max_tokens: 300 }21  agenda:22    with:23      calendar: ${{ tasks.calendar.output }}24    ◇infer: { prompt: "Plan the day around: ${{ with.calendar }}", max_tokens: 300 }2526  draft:27    with:28      notes: ${{ tasks.notes.output }}29      triage: ${{ tasks.triage.output }}30      agenda: ${{ tasks.agenda.output }}31    ◇infer:32      prompt: "Write the morning brief. Notes: ${{ with.notes }} Urgent: ${{ with.triage }} Plan: ${{ with.agenda }}"33      max_tokens: 5003435  save:36    with:37      draft: ${{ tasks.draft.output }}38    ◆invoke:39      tool: "nika:write"40      args: { path: ./brief.md, content: "${{ with.draft }}" }4142outputs:43  brief: "${{ tasks.draft.output }}"44

source

Watch the file become the run.

1nika: v12workflow:3  id: daily-brief4# local model · your notes never leave5model: ollama/llama3.2:3b67# the file IS the blast radius8permits:9  fs: { read: [ ./notes/* ], write: [ ./brief.md ] }10  tools: [ "nika:read", "nika:write" ]1112tasks:13  notes: { ◆invoke: { tool: "nika:read", args: { path: ./notes/today.md } } }14  inbox: { ◆invoke: { tool: "nika:read", args: { path: ./notes/inbox.md } } }15  calendar: { ◆invoke: { tool: "nika:read", args: { path: ./notes/calendar.md } } }1617  triage:18    with:19      inbox: ${{ tasks.inbox.output }}20    ◇infer: { prompt: "Flag what is urgent: ${{ with.inbox }}", max_tokens: 300 }21  agenda:22    with:23      calendar: ${{ tasks.calendar.output }}24    ◇infer: { prompt: "Plan the day around: ${{ with.calendar }}", max_tokens: 300 }2526  draft:27    with:28      notes: ${{ tasks.notes.output }}29      triage: ${{ tasks.triage.output }}30      agenda: ${{ tasks.agenda.output }}31    ◇infer:32      prompt: "Write the morning brief. Notes: ${{ with.notes }} Urgent: ${{ with.triage }} Plan: ${{ with.agenda }}"33      max_tokens: 5003435  save:36    with:37      draft: ${{ tasks.draft.output }}38    ◆invoke:39      tool: "nika:write"40      args: { path: ./brief.md, content: "${{ with.draft }}" }4142outputs:43  brief: "${{ tasks.draft.output }}"44

[ 01 ]run together ×3

notesinvokenika:read✓ 3ms

inboxinvokenika:read✓ 1ms

calendarinvokenika:read✓ 1ms

[ 02 ]run together ×2

triageinferollama/llama3.2:3b✓ 29.2s

agendainferollama/llama3.2:3b✓ 27.0s

[ 03 ]then

draftinferollama/llama3.2:3b✓ 29.6s

[ 04 ]then

saveinvokenika:write✓ 14ms

daily-brief.nika.yaml

nika run daily-brief.nika.yaml

workflow daily-brief

scheduled 7 tasks · notes inbox calendar triage agenda draft save

notes invoke · nika:read

notes 3ms

inbox invoke · nika:read

inbox 1ms

calendar invoke · nika:read

calendar 1ms

triage infer · ollama/llama3.2:3b

triage 29.2s · 29 tok

agenda infer · ollama/llama3.2:3b

agenda 27.0s · 300 tok

draft infer · ollama/llama3.2:3b

draft 29.6s · 260 tok

save invoke · nika:write

save 14ms

run complete · exit 0 · 58.7s

✓ exit 07 tasks ran58.7swrote brief.md$0.00localollama/llama3.2:3b

recorded · nothing staged

recorded from a real nika run · replayed by your scroll · nothing staged

01.1

Press play. It really ran.

The same file, executed by the engine with a local model on a real machine. What you watch is the recorded event stream.

daily-brief.nika.yaml

nika run daily-brief.nika.yaml

workflow daily-brief

scheduled 7 tasks · notes inbox calendar triage agenda draft save

notes invoke · nika:read

notes 3ms

inbox invoke · nika:read

inbox 1ms

calendar invoke · nika:read

calendar 1ms

triage infer · ollama/llama3.2:3b

triage 29.2s · 29 tok

agenda infer · ollama/llama3.2:3b

agenda 27.0s · 300 tok

draft infer · ollama/llama3.2:3b

draft 29.6s · 260 tok

save invoke · nika:write

save 14ms

run complete · exit 0 · 58.7s

✓ exit 07 tasks ran58.7swrote brief.md$0.00 · ollama/llama3.2:3b

recorded from a real nika run · replayed at reading pace · nothing staged

01.2

One file. A plan you can read.

The engine derives the order from the wiring: a with: binding is a data edge, an after: entry a control edge. Steps with no edge between them run together. Nothing runs that is not written in the file.

[ 01 ]run together ×3

notesinvokenika:read✓ 3ms

inboxinvokenika:read✓ 1ms

calendarinvokenika:read✓ 1ms

[ 02 ]run together ×2

triageinferollama/llama3.2:3b✓ 29.2s

agendainferollama/llama3.2:3b✓ 27.0s

[ 03 ]then

draftinferollama/llama3.2:3b✓ 29.6s

[ 04 ]then

saveinvokenika:write✓ 14ms

durations recorded from the real run · hover a step to trace its wires

[ THE BOUNDARY ]

What it's allowed to touch.

The permits: block is part of the file you review. It is the whole list. Everything not on it is denied by default, before it runs. The full reference · families, secrets, the always-on floor · lives at /boundary.

daily-brief.nika.yaml · lines 8–10

8permits:9  fs: { read: [ ./notes/* ], write: [ ./brief.md ] }10  tools: [ "nika:read", "nika:write" ]

the same file as above · the permits block, verbatim

don't write it by hand:nika check --infer-permitsprints the tightest boundary the plan needs. Paste it in, loosen it yourself, or leave it strict.

fs:which files it may read and write
tools:which tools it may call

if a step reaches outside the list, say

✗write ~/.ssh/config   NIKA-SEC-004

effect outside the declared permits: capability boundary. Blocked before it runs, never logged after the fact. (An example: the recorded run above stayed in bounds, exit 0.)

4 verbs · locked forever
28 builtins
17 providers · local-first
one Rust binary
AGPL-3.0 forever
supernovae-st/nika
every claim, one graph · /map

Chats evaporate. Files compound. The prompts you perfect, the steps an agent improvises: gone with the session. Nika turns that work into a file: readable, versioned, runnable.

daily-brief.nika.yaml

1nika: v12workflow:3  id: daily-brief4# local model · your notes never leave5model: ollama/llama3.2:3b67# the file IS the blast radius8permits:9  fs: { read: [ ./notes/* ], write: [ ./brief.md ] }10  tools: [ "nika:read", "nika:write" ]1112tasks:13  notes: { ◆invoke: { tool: "nika:read", args: { path: ./notes/today.md } } }14  inbox: { ◆invoke: { tool: "nika:read", args: { path: ./notes/inbox.md } } }15  calendar: { ◆invoke: { tool: "nika:read", args: { path: ./notes/calendar.md } } }1617  triage:18    with:19      inbox: ${{ tasks.inbox.output }}20    ◇infer: { prompt: "Flag what is urgent: ${{ with.inbox }}", max_tokens: 300 }21  agenda:22    with:23      calendar: ${{ tasks.calendar.output }}24    ◇infer: { prompt: "Plan the day around: ${{ with.calendar }}", max_tokens: 300 }2526  draft:27    with:28      notes: ${{ tasks.notes.output }}29      triage: ${{ tasks.triage.output }}30      agenda: ${{ tasks.agenda.output }}31    ◇infer:32      prompt: "Write the morning brief. Notes: ${{ with.notes }} Urgent: ${{ with.triage }} Plan: ${{ with.agenda }}"33      max_tokens: 5003435  save:36    with:37      draft: ${{ tasks.draft.output }}38    ◆invoke:39      tool: "nika:write"40      args: { path: ./brief.md, content: "${{ with.draft }}" }4142outputs:43  brief: "${{ tasks.draft.output }}"44

the session ends · the file stays

Seeing the steps is not the same as enforcing them. Here is what each black box trades away.

Chat sessions

Great for exploring
Gone when the tab closes
Different answer every time

A file you keep

Runs again tomorrow
Same steps, same order
Diff it like code

Glue scripts

200 lines of Python + retries
One person understands it
Breaks when an API changes

Four verbs

The YAML is the logic
Anyone can read it
Engine handles retries & order

Cloud automations

Runs on their servers
Per-seat, per-run pricing
Your data leaves the building

Your machine

One binary, runs local
Free, AGPL forever
Nothing leaves unless you say so

The run explains itself.

One file ran once: audited before it started, storyboarded while it ran, replayable after it ended. Every frame below is real output of the real binary, captured on a terminal against committed fixtures. Offline, on the mock model, for zero dollars. How the proof works · graph, receipt, conformance · lives at /proof.

recorded from a real nika run · replayed at reading pace · nothing staged

Terminal capture of nika check on the signature workflow: the audit ladder passes with a cost floor warning and one permits hint, rc=0. — the pre-flight ladder: plan · cost · secrets · types · tools · args · schema · permits, then one hint. rc=0.

What an agent can do. Declared, not hidden.

Four verbs are the only native execution models. Every action explicit and typed, never improvised from a hidden prompt. Everything callable is a tool under invoke, and tools are allow-listed. Everything about ordering is the plan: which tasks wait on which. No fifth verb, ever.

5.1infer

Think. Ask any model · local or cloud.

5.1.1 providers5.1.2 structured output5.1.3 local models

think.nika.yaml

1nika: v12workflow:3  id: think4model: ollama/llama3.2:3b5tasks:6  summarize:7    ◇infer:8      prompt: "Three risks in this release, ranked"

5.2exec

Run. A shell command, captured and typed.

5.2.1 capture & exit codes5.2.2 retry · timeout5.2.3 permitted programs

run.nika.yaml

1nika: v12workflow:3  id: run4tasks:5  build:6    ▷exec:7      command: ["cargo", "build", "--release"]

5.3invoke

Use a tool. Fetch a page, write a file, call GitHub. Every tool explicit.

5.3.1 builtins5.3.2 extract modes5.3.3 MCP servers

use-a-tool.nika.yaml

1nika: v12workflow:3  id: use-a-tool4tasks:5  page:6    ◆invoke:7      tool: "nika:fetch"8      args: { url: "https://nika.sh" }

5.4agent

Delegate. An autonomous loop, on a leash you can read.

5.4.1 tool allow-list5.4.2 max turns5.4.3 the human gate

delegate.nika.yaml

1nika: v12workflow:3  id: delegate4model: ollama/llama3.2:3b5tasks:6  audit:7    ✦agent:8      prompt: "Find every dead link in ./docs"9      tools: [ "nika:read", "nika:fetch" ]

infer ◇ · exec ▷ · invoke ◆ · agent ✦ · the whole operation space, declared in one file

What an agent can be permitted to use.

The language stays four verbs. The standard library does the rest: 28 builtins, 17 model providers, and any of your agent tools (MCP servers) your editor already uses. All reached the same way: invoke:, and none of it runs unless the file's permits: allows it.

0128builtin tools · nothing to install

0217model providers · 5 local, 11 cloud, 1 mock

039extract modes on fetch

04MCPnativeyour agent tools (MCP) · any server, via the same verb

BuiltinsThe everyday tools. All called with invoke:.28 tools · 4 families

Files· 5

read· read a filewrite· save a fileedit· patch a fileglob· find filesgrep· search text

Data· 9

jq· transform JSONconvert· between formatsvalidate· check a schemajson_diff· what changedjson_merge_patch· merge JSONcompose· chain toolshash· fingerprint datauuid· fresh iddate· now · parse · format

Web· 1

fetch· get a page · 9 extract modes

Flow· 13

assert· check a conditiondone· end the loopwait· pauseemit· send an eventlog· say somethingnotify· ping a humanprompt· ask a humaninspect· debug a valuechart· see the docsdecide· see the docsimage_fx· see the docsimage_generate· see the docstts_generate· see the docs

ProvidersPick per task or per file. provider: ollama runs offline.17 total

Local runtimes· 5 · no cloud needed

OllamaLM Studiollama.cppLocalAIvLLM

Cloud · open-weight first· 11

MistralAnthropicOpenAIGeminiDeepSeekxAIGroqOpenRouterhuggingfacenvidiamoonshot

Test· 1

mock· deterministic · zero keys · CI-runnable

Extract modesHow fetch turns a page into typed output.9 modes

articlefeedjqlinksmarkdownmetadataselectorsitemaptext

MCPAny of your agent tools (MCP servers), reached as mcp:.native · unbounded

mcp:· the server your editor already usesstdiohttpdefault-deny· tools whitelisted in the file

every count derives from the spec's canon.yaml · never hand-typed

Not another agent framework. The layer underneath.

Frameworks and assistants help an agent decide and act. Nika is orthogonal: it makes what the agent does reviewable and enforceable the layer between the model wants to act and the system lets it act.

FrameworksLangGraph, n8n: they help you wire and orchestrate the steps.: Nika makes the wired steps a reviewable, enforceable file, not glue code.
AssistantsCursor, Claude Code: they help an agent decide and act in the moment.: Nika turns that intent into a plan you review and the runtime enforces.
Protocols & toolsYour agent tools (MCP servers) expose capabilities an agent can call.: Nika runs them through invoke: allow-listed, permission-bound, traced.

Run a Nika plan from any of them. It's a portable file, not a platform.

nika: v1
workflow:
  id: standup-digest
  description: "Read yesterday's commits, write today's standup note"

model: ollama/qwen3.5:4b   # local · zero key · swap for anthropic/claude-haiku-4-5 (fast one-liner job)

tasks:
  # No deps between these two → the engine runs them in parallel.
  today:
    invoke:
      tool: "nika:date"
      args: { op: now }

  history:
    exec:
      command: ["git", "log", "--since=yesterday", "--oneline", "--no-merges"]

  digest:
    with:
      today: ${{ tasks.today.output }}
      history: ${{ tasks.history.output }}
    infer:
      prompt: |
        Date · ${{ with.today }}
        Commits since yesterday ·
        ${{ with.history }}

        Write my standup note · 3 bullets · done / doing / blocked.
        Plain words · no fluff.

  save:
    with:
      digest: ${{ tasks.digest.output }}
    invoke:
      tool: "nika:write"
      args:
        path: "./standup-note.md"
        content: "${{ with.digest }}"

outputs:
  note: ${{ tasks.digest.output }}

Real files you'd write.

Anything you'd ask an AI to do more than once belongs in a file. Every workflow below is real, projected from nika-spec, audited before it runs: plan, cost, secrets. Pick your métier, open a card, read the exact YAML that runs it.

Ship faster. Let the boring parts run themselves.

t1-standup-digest.nika.yamlwalkthrough ↗

todayinvokenika:datehistoryexecgit

digestinfer

saveinvokenika:write

yaml

1nika: v12workflow:3  id: standup-digest4  description: "Read yesterday's commits, write today's standup note"56model: ollama/qwen3.5:4b   # local · zero key · swap for anthropic/claude-haiku-4-5 (fast one-liner job)78tasks:9  # No deps between these two → the engine runs them in parallel.10  today:11    ◆invoke:12      tool: "nika:date"13      args: { op: now }1415  history:16    ▷exec:17      command: ["git", "log", "--since=yesterday", "--oneline", "--no-merges"]1819  digest:20    with:21      today: ${{ tasks.today.output }}22      history: ${{ tasks.history.output }}23    ◇infer:24      prompt: |25        Date · ${{ with.today }}26        Commits since yesterday ·27        ${{ with.history }}2829        Write my standup note · 3 bullets · done / doing / blocked.30        Plain words · no fluff.3132  save:33    with:34      digest: ${{ tasks.digest.output }}35    ◆invoke:36      tool: "nika:write"37      args:38        path: "./standup-note.md"39        content: "${{ with.digest }}"4041outputs:42  note: ${{ tasks.digest.output }}43

Every morning: the note is already written. You glance, you tweak one word, you go.

26 workflows · four tiers · nika-spec/examples/showcase the plan, the typed answers and the tools, all checked before it runs

The file becomes a canvas. Open any `.nika.yaml` in VS Code or Cursor: prompts sit on the cards, a run lights the graph wave by wave, and every canvas edit lands back in the file. This miniature works: press ▶ mock.

release-notes.nika.yaml · canvashover a card; its lineage stays lit

$0.00 ceiling · local model · audited before it runs

release-notes.nika.yaml

nika: v1
workflow:
  id: release-notes
model: ollama/qwen3.5:4b

tasks:
  fetch_commits:
    invoke:
      tool: "nika:fetch"
      args:
        url: "https://api.github.com/repos/acme/app/commits?since=v1.4.0"

  write_notes:
    with:
      commits: ${{ tasks.fetch_commits.output }}
    infer:
      max_tokens: 800
      prompt: "Write the release notes from ${{ with.commits }}: grouped, human, no hype."

  hero_image:
    after:
      fetch_commits: succeeded
    invoke:
      tool: "nika:image_generate"
      args:
        provider: local
        prompt: "A minimal banner for the v1.5 release"
        aspect_ratio: "16:9"
        output_dir: "media/"

  publish:
    after:
      write_notes: succeeded
      hero_image: succeeded
    exec:
      command: ["gh", "release", "create", "v1.5.0", "--notes-file", "notes.md"]

The engine's judgment, as you type. Diagnostics, completions and hovers come from nika check and the schema: codes, fixes and positions are the binary's, not the extension's. Even this demo file passes the real nika check, exit 0.
Run, replay, scrub. The run streams onto the graph live; any recorded run replays with a time-travel scrubber.
Audited before a token is spent. Cost ceiling, permits boundary and secret flows are static facts on the cards. Read them before you press Run.

Install in VS Code Marketplace Open VSX · Cursor / Windsurf

Shipping in the open.

A workflow language earns trust by moving, and by not breaking what you wrote. Here is the recent ship log: the spec opened, the verbs locked: and the engine shipped, one brew install away.

2026 · 07 · 20release
v0.105.0 · the map comes home
The refonte reaches users: the file becomes a map. workflow: is an object (id + description), tasks: is a map keyed by id, and precedence reads the way you think: the binding IS the edge (with: declares the data edge) while control-only ordering is after: {producer: succeeded} against a closed predicate set. The old forms die loudly (a scalar workflow: is NIKA-PARSE-020, depends_on: is NIKA-PARSE-024) and nika check --fix machine-migrates the provable cases. The proof layer opens: semantic hash, nika.lock, receipt_format: 1, workflow composition (invoke: workflow:), and nika:decide, the deterministic decision kernel. One security seat ships in the tag: the lethal-trifecta judge (NIKA-SEC-009) refuses private-read plus untrusted-ingress plus external-egress with no blocking human gate on the path. The LSP learns the map end to end: server-side rename, per-block keysets, semantic_document_format: 1. Every surface you copy from re-baked the same day; what you copy runs on YOUR installed binary.
2026 · 07 · 17release
v0.104.0 · kimi takes a priced seat
Moonshot joins the canonical catalog: model: moonshot/kimi-k3 runs first-class (1M context, MOONSHOT_API_KEY), and the pricing snapshot makes --max-cost-usd a hard ceiling on kimi spend (the promotion run metered real cents against a printed worst case). K3 is a thinking model, and the honesty ships with it: reasoning spends output tokens, so budget max_tokens generously; starved, the answer comes back empty and the engine says why. The release branch cut from v0.103.0 on purpose: main is mid-refonte and users never ship a transitional grammar. Also in the wave: the lsp, graph and mcp fixtures that shipped red at the previous tag now speak the argv form, banked as a CI-coverage finding.
2026 · 07site
nika.sh v4.18 · the site speaks the shipped grammar
The 0.104 release flipped the language: the envelope became a scalar (workflow: my-job), tasks became a sequence (- id: …), and every edge is declared (depends_on — an undeclared tasks.X read now dies at check as NIKA-DAG-003; after: died with it). The public spec still teaches the old form, so the site now runs on TWO spec surfaces and says so out loud: /spec/v1 stays the ratified pin, /spec/shipped vendors what the released binary itself embeds (nika spec --schema and --canon, refreshed deliberately, never probed at build), and /sources renders the grammar gap as a third clock line beside builtins and providers. Everything a visitor can copy speaks the shipped grammar and is PROVEN against the released binary: every hero flagship and its served /library file, the /learn walk and its assembled weekly radar, both install hellos with transcripts re-captured verbatim, the verb chapters, the 404, the /convert proof, and every showcase room and template seed, which stay byte-pure ratified projections and convert at the door through one mechanical, idempotent, line-mapped pass — the plan choreography, the hero highlights and the inspector line anchors all re-aim through the same map, so nothing drifts from the text it animates. The playground lint learned the new world (scalar envelope, sequence tasks, duplicate ids, declared-edge DAG-003, after: refused with its fix line), its break-lesson inverted to teach the flip, and a shipped-ahead door renders text-only until the spec lands the room. Alongside the flip: the engine badge reads v0.104.0 everywhere, the tools register carries decide as ratified-not-shipped with its spec contract on the page, the types register lands its primitives read from the schema itself (the last soon chip dies), the provider catalog re-vendors at 0.104, and the hub headers stop sliding under the fixed nav.
2026 · 07 · 13release
v0.103.0 · the language tightens
The pre-1.0 window pays for itself: three breaking cuts in one wave, spec and engine merged in the same window. command: is argv-only (execve, no shell: an interpolated value can never break out of its argument) and the string form moves to shell:, the explicit door; semantics ride the field, never the YAML type. A bare ${{ tasks.X }} is now an error (NIKA-VAR-020): name the projection (.output, .status, .error, .duration_ms); the envelope is not a value. And the gate algebra becomes a normative spec table: the when-status pattern is a propagation choice, not redundancy. The whole corpus migrated in lockstep: docs, site, editor, kit and registry re-taught the same day.

Full changelog

The control is the proof.

No logos to borrow, no quotes to dress up. Just what the engine guarantees: review before it acts · enforced permissions · replayable trace · portable off any platform · versioned like code: verifiable in the open spec and the one binary you install.

9.14verbs · every action explicit, declared not hidden

9.228builtin tools · allow-listed, nothing to install

9.317/5 localmodel providers · any model, cloud or fully offline

9.41Rust binary · zero daemons, zero background services

Review before it acts.: The agent writes its plan as a file first: every step, tool and permission. A human reads it before a single action runs.
Enforced permissions.: The file's permits: block is the blast radius: files, hosts, programs, tools. The runtime denies anything outside it (5 local providers mean PII never has to leave).
Replayable trace.: Every run leaves a replayable record, the audit trail. Same file, same steps, same order: run it again and diff it like code.
Portable off any platform.: One binary, 17 model providers, AGPL-3.0 forever. The file outlives the vendor. It still runs the day the company that made it is gone.

A README is documentation. Nika is an executable contract.

every number derives from the spec's canon.yaml · verifiable, never hand-typed

Get started.

One binary, one file, one command. Install it, write a plan, run it, and watch it print the plan, check the permits, and stay within bounds.

Install
One Rust binary. Homebrew on macOS, or the install script anywhere.
brew install supernovae-st/tap/nika
curl -LsSf https://nika.sh/install.sh | sh

Write a file

A plan is plain YAML: the steps, the verbs, the wiring. This is the same file the page just ran, opened at its first step.

daily-brief.nika.yaml · excerpt

1nika: v12workflow:3  id: daily-brief4…5permits:6  fs: { read: [ ./notes/* ], write: [ ./brief.md ] }7  tools: [ "nika:read", "nika:write" ]8…9  notes: { ◆invoke: { tool: "nika:read", args: { path: ./notes/today.md } } }

real lines, sliced from the file above · read-only

Run it
Point the binary at the file. It prints the plan, checks the permits, and runs within bounds. Every step traced and replayable.
nika run daily-brief.nika.yaml

runs everywhere · same file, same result

6.0.4 In your terminal

One Rust binary. The command is the button: click it, paste it, run.

6.0.5 In your editor

The nika-lang extension: the file as a content-first canvas. Run it live, replay it, audit it before a token is spent, with engine-true diagnostics and completions, in VS Code, Cursor and Windsurf.

VS Code Marketplace Open VSX · Cursor / Windsurf

6.0.6 With your agent

nika init writes AGENTS.md · nika wire claude|cursor adds the read-only oracle (nika_check · nika_explain).

docs.nika.sh

WORKS WITH YOUR STACK

Claude Code · Codex · Cursor · VS Code · Hermes · OpenCode · Zed · GitHub Actions · MCP

nika init teaches whatever agent you run. the full integrations map

Learn it in 5 minutes

Questions, answered straight.

The real objections, and honest answers. No overclaiming, no dunking on the tools you already use.

I already see the agent’s steps in Cursor or a README. Why Nika?
Seeing the steps is not the same as enforcing the procedure. A README is documentation; a Nika file is an executable contract: versionable, replayable, permission-bound, auditable, and portable off any platform. You do not just read what it intends to do; the runtime holds it to exactly that.
Isn’t this just YAML, or another workflow engine?
The syntax is plain YAML, but the point is not the syntax. The point is the reviewable, enforced plan. The 4 verbs (infer · exec · invoke · agent) are native execution models, each one explicit and typed, with a permits: block the runtime enforces before anything runs. The file is the control surface, not the formatting.
Why not LangGraph, n8n, or MCP (agent tools)?
They live at a different layer. Frameworks help you orchestrate and assistants help an agent act; MCP exposes tools to call. Nika is the contract-and-control layer underneath: it makes the plan reviewable and enforceable, and it runs their tools through invoke, allow-listed and traced. It complements them rather than replacing them.
Does my data leave my machine?
Local-first, any model: fully local, or any API. Run a local model and nothing leaves at all. Every plan declares its network egress in its permits: block, and it is default-deny: omit the hosts and the workflow physically cannot reach the network. The file states exactly what can leave, and the runtime enforces it. 5 of the 17 providers are local.
Is it production-ready? What’s the license?
Honest answer: Nika is early. Real semver toward a 1.0 launch, currently at v0.105.0, shipping in the open. It is one Rust binary you can install and run today. The engine is AGPL-3.0-or-later; the spec is Apache-2.0. We would rather you trust the spec and the binary than a maturity claim we have not earned yet.

the noise becomes the file.

Put your agents on a leash you can read.

Install the binary, write the plan as a file, review what it's allowed to touch, run it. Same file, same result, enforced on your machine. Tomorrow, and the day the vendor is gone.

brew install supernovae-st/tap/nika

Star on GitHub Read the spec Learn it in 5 min

Do you repeat an AI task every week, in ChatGPT, Claude, Cursor, Codex, or scripts? Send it. We convert the best ones into runnable .nika.yaml examples, credited to you.

Send a workflow

Useful AI work shouldn’t disappear into chats.

Press play. It really ran.

One file. A plan you can read.

What it's allowed to touch.

Chats evaporate. Files compound. The prompts you perfect, the steps an agent improvises: gone with the session. Nika turns that work into a file: readable, versioned, runnable.

The run explains itself.

What an agent can do. Declared, not hidden.

What an agent can be permitted to use.

Not another agent framework. The layer underneath.

Real files you'd write.

The file becomes a canvas. Open any .nika.yaml in VS Code or Cursor: prompts sit on the cards, a run lights the graph wave by wave, and every canvas edit lands back in the file. This miniature works: press ▶ mock.

Shipping in the open.

v0.105.0 · the map comes home

v0.104.0 · kimi takes a priced seat

nika.sh v4.18 · the site speaks the shipped grammar

v0.103.0 · the language tightens

The control is the proof.

Get started.

Install

Write a file

Run it

6.0.4 In your terminal

6.0.5 In your editor

6.0.6 With your agent

Questions, answered straight.

Put your agents on a leash you can read.

The file becomes a canvas. Open any `.nika.yaml` in VS Code or Cursor: prompts sit on the cards, a run lights the graph wave by wave, and every canvas edit lands back in the file. This miniature works: press ▶ mock.