v2.0.1 — plan before edit, verify after edit

Plan before edit.
Verify after edit.

Open Kioku is the local evidence layer for Claude, Cursor, Codex, and other MCP coding agents. It indexes your repo once, builds evidence-backed plans before edits begin, then verifies bounded changes stayed inside the plan. No cloud. No source upload. Read-only by default.

1 index
local SQLite and Tantivy facts for the repo
0 cloud
no embeddings API or hosted code index required
read-only
write tools stay gated unless explicitly enabled
Public Repository Testing

Tested across several large public repositories.

The metrics below are from one representative local run with Open Kioku 2.0.1. The full audit includes source-checked results and documented limitations across languages. Read the full audit →

4,623
files indexed
46,738
symbols extracted
49,459
chunks stored
8,945
tests indexed
79,426
graph edges
33.1s
local index time
If Open Kioku helps your agent workflow, consider starring it on GitHub. ⭐ Star on GitHub
Why not just grep / repo map / RAG?

Search finds code. Planning knows what to do with it.

Grep finds text. Repo maps outline files. Open Kioku gives agents a reliable pre-edit routine: indexed evidence → symbols → impact → tests → plan → verify.

Typical agent loop

  • !Repeated grep, glob, and read calls burn context before the agent understands the repo.
  • !References are inferred from text matches instead of symbols, imports, and persisted graph edges.
  • !Test selection often happens after the edit, when the agent has already guessed wrong.

Open Kioku loop

  • OKOne indexed search returns ranked evidence and exact file ranges.
  • OKSymbol, reference, impact, and architecture tools share the same local index.
  • OKPlans include affected files, edit boundaries, validation candidates, and agent tool calls before edits start.
Live Workflow

The pre-edit routine agents should run every time.

Install Open Kioku, index a real repo, verify the index, connect MCP, then ask the agent to plan from indexed evidence before editing.

ok setup --agent
Workflow

One indexed path from question to validation.

The strongest product story is not search alone. It is the complete loop a coding agent needs before making a change.

1

Find evidence

Search code and files with ranked snippets, line ranges, and confidence signals.

2

Resolve symbols

Jump to definitions and references without asking the model to infer ownership from text.

3

Trace impact

Use local graph facts to identify changed files, affected modules, and likely callers.

4

Validate edits

Build context packs and pre-edit plans that keep agents focused on the smallest useful surface.

Example Output

What an evidence-backed plan looks like.

Open Kioku generates structured, markdown-compatible plans that AI agents use to establish edit boundaries, target tests, and assess confidence before touching files.

ok plan "update token expiration"
# Plan: token

Found 5 primary context item(s), 3 direct impact candidate(s), 2 validation candidate(s)

## Risk
- Level: `low`
- Score: `0.10`

## Confidence
- Overall: `High` (`0.81`)
- Caveats:
  - exact symbol/reference evidence is absent
  - runtime corroboration is absent

## Primary Context
- `src/auth.rs`:7-11: pub fn validate_token(token: &str) -> bool
- `tests/auth_flow.rs`:4-7: fn login_returns_valid_token()
- `src/auth.rs`:3-6: pub fn issue_token(context: &RequestContext, ttl_seconds: u64) -> String

## Impact Candidates
- `src/session.rs` — caller dependency of validate_token
- `src/middleware.rs` — route guard dependency of issue_token

## Validation Targets
- `cargo test auth_flow`
- `cargo test token_expiration`

## Boundary Policy
- Allowed: `src/auth.rs`, `tests/auth_flow.rs`
- Caution: `src/session.rs` (caller)
- Forbidden: `generated/`, `vendor/`
Real Repo Setup

Index first, then connect your LLM.

Use this path for an existing codebase. The MCP config points your agent at the same local index that the CLI verifies.

Build and verify the index
ok init /absolute/path/to/repo
ok index /absolute/path/to/repo
ok doctor /absolute/path/to/repo
ok --repo /absolute/path/to/repo search "feature or bug" --limit 5
Prompt the agent
Use Open Kioku before editing. Check repo_status, search_code, get_definition,
get_references, impact_analysis, and find_tests_for_change. Build a plan first,
then edit only after the indexed evidence is clear.
Shareable Proof

Show usefulness without posting source code.

Run `ok prove` on a demo repo or private codebase to produce a Markdown report with indexed counts, task scores, validation signals, and redacted path shapes. The report intentionally omits source snippets.

Demo proof
ok prove ./open-kioku-demo --task token
Private repo proof
ok prove /path/to/repo --task "auth flow" --task "release workflow"
Connect

Copy-paste setup for every major MCP client.

Open Kioku runs as a local MCP server over stdio. These commands print client-specific configuration; they do not edit your config files automatically.

Cursor
ok mcp install cursor --repo /absolute/path/to/repo
Claude Code
ok mcp install claude --repo /absolute/path/to/repo
Codex
# Install Git-scoped plugin (Recommended):
codex plugin marketplace add shivyadavus/open-kioku
# Or configure manual MCP server:
ok mcp install codex --repo /absolute/path/to/repo
Gemini CLI
ok mcp install gemini --repo /absolute/path/to/repo
OpenCode
ok mcp install opencode --repo /absolute/path/to/repo
Zed
ok mcp install zed --repo /absolute/path/to/repo
Windsurf
ok mcp install windsurf --repo /absolute/path/to/repo
Trae
ok mcp install trae --repo /absolute/path/to/repo
Safety

Built for codebases people cannot upload.

The trust message matters as much as the speed message. Open Kioku is designed for local indexing, explicit write controls, and predictable MCP behavior.

No hosted index

Metadata stays under `.ok/` in your repo. There is no hosted search service to provision or trust.

No embeddings API required

BM25 search, symbols, and graph operations work locally without uploading code to a model provider.

Write tools gated

Patch and command paths are opt-in, policy-controlled, and separate from read-only context tools.

Quality

Every commit tested, audited, and benchmarked.

CI on Ubuntu + macOS
cargo audit + cargo deny
20/20 usefulness proof tasks
Cursor + Claude smoke tests
Criterion benchmark gates
Workflow-bench regression suite
Golden snapshot coverage
SHA-256 checksummed release binaries