xint
Local-first X Intelligence CLI for search, monitoring, analysis, exports, OAuth actions, and agent tooling.
Local policy, evidence, and recovery controls for coding agents. LACP wraps Claude, Codex, Hermes, and other CLI agents with deterministic routing, approval gates, execution records, memory controls, and rollback paths.
> /plugin marketplace add 0xNyk/lacp> /plugin install lacp-hardening@lacp-plugins
Repo: 0xNyk/lacp
What's inside
Local policy, evidence, and recovery controls for coding agents.
LACP wraps Claude, Codex, Hermes, and other CLI agents with deterministic routing, approval gates, execution records, memory controls, and rollback paths. It runs on your machine and keeps remote execution opt-in.

Development status:
mainreports version 0.10.0. The latest published GitHub and Homebrew release is v0.6.0. Main includes unreleased changes and may alter commands or configuration before the next release. Use the Homebrew package when you need the published release; use--HEADonly when you want current development code.
LACP is a local execution wrapper and control plane. The coding-agent host still owns its model, tools, session, and interface. LACP owns the contract around a run: where it may execute, which risk tier applies, when approval is required, what evidence must be kept, and how a failed change is recovered.

# Homebrew (recommended)
brew tap 0xNyk/lacp && brew install lacp
# or inspect and run the bootstrap at a published tag
curl -fsSLo /tmp/lacp-install.sh \
https://raw.githubusercontent.com/0xNyk/lacp/v0.6.0/install.sh
LACP_REF=v0.6.0 bash /tmp/lacp-install.sh
lacp bootstrap-system --profile starter --with-verify
lacp doctor --json | jq '.ok,.summary'
After bootstrap: .env is created, dependencies installed, directories scaffolded, Obsidian vault wired, and verification artifacts produced.
For the full setup and daily operator flow, start with the Runbook and Local Dev Loop.
# Route a task through LACP policy gates
lacp run --task "hello world" --repo-trust trusted -- echo "LACP is working"
# Make claude/codex/hermes default to LACP routing (reversible)
lacp adopt-local --json | jq

lacp bootstrap-system --profile starter --with-verify
lacp adopt-local --json | jq
lacp posture --strict
lacp run \
--task "dependency update with tests" \
--repo-trust trusted \
--context-profile default \
-- pnpm up && pnpm test
lacp e2e smoke --workdir . --init-template --command "npx playwright test --grep @smoke"
lacp api-e2e smoke --workdir . --init-template --command "npx schemathesis run --checks all"
lacp pr-preflight --changed-files ./changed-files.txt --checks-json ./checks.json
lacp worktree create --repo-root . --name feature-a --base HEAD
lacp up --session feature-a --instances 3 --command "claude"
lacp swarm launch --manifest ./swarm.json
| Guide | What You'll Learn |
|---|---|
| Runbook | Daily operator workflow, command map, troubleshooting entry points |
| Local Dev Loop | Fast build/test/verify loop for contributors |
| Framework Scope | What LACP is, what it is not, and design boundaries |
| Implementation Path | Step-by-step rollout plan for full control-plane adoption |
| Memory Quality Workflow | How memory ingestion, expansion, and validation are run safely |
| Incident Response | Triage and recovery flow when policy gates fail |
| Release Checklist | Pre-release, release, and post-release controls |
| Troubleshooting | Common errors, doctor diagnostics, fix hints |
lacp/
โโโ bin/ # CLI commands (lacp <command>)
โ โโโ lacp # Top-level dispatcher
โ โโโ lacp-bootstrap-system
โ โโโ lacp-doctor # Diagnostics (--json, --fix-hints)
โ โโโ lacp-route # Policy-driven tier/provider routing
โ โโโ lacp-sandbox-run # Gated execution with artifact logging
โ โโโ lacp-brain-* # Memory stack (ingest, expand, doctor, stack)
โ โโโ lacp-obsidian # Vault config management
โ โโโ lacp-up # Multi-instance agent sessions
โ โโโ lacp-swarm # Batch orchestration
โ โโโ lacp-claude-hooks # Hook profile management
โโโ config/
โ โโโ sandbox-policy.json # Routing + cost ceilings
โ โโโ risk-policy-contract.json
โ โโโ obsidian/ # Vault manifest + optimization profiles
โ โโโ harness/ # Task schemas, sandbox profiles, verification policies
โโโ hooks/ # Python hook pipeline for Claude Code
โโโ scripts/
โ โโโ ci/ # Test suites
โ โโโ runners/ # Daytona/E2B execution adapters
โโโ docs/ # Guides and reference docs
Agent invocation
โ lacp route (risk tier + provider selection)
โ context contract validation
โ budget gate check
โ session fingerprint verification
โ sandbox-run (dispatch + artifact logging)
Every command routes through risk tiers (safe โ review โ critical), budget ceilings per tier, and context contracts that validate host, working directory, git branch, and remote targets before execution.

| Layer | Purpose |
|---|---|
| Session memory | Per-project scaffolding under ~/.claude/projects/ |
| Knowledge graph | Obsidian vault with MCP wiring (smart-connections, QMD, ori-mnemos) |
| Ingestion pipeline | brain-ingest converts text/audio/video/URLs into structured notes |
| Code intelligence | GitNexus AST-level knowledge graph via MCP (optional) |
| Agent identity | Persistent IDs per (hostname, project) + SHA-256 hash-chained provenance |
lacp brain-stack init --json | jq # Bootstrap all layers
lacp brain-ingest --url "https://..." --apply --json | jq
lacp brain-expand --apply --json | jq # Full expansion loop
Modular Python hooks enforcing quality at every session stage:
| Hook | Event | Purpose |
|---|---|---|
session_start.py | SessionStart | Git context injection, test command caching |
pretool_guard.py | PreToolUse | Block dangerous operations (publish, chmod 777, fork bombs, secrets) |
write_validate.py | PostToolUse | YAML frontmatter schema validation |
stop_quality_gate.py | Stop | 3-tier eval: heuristics, test verification, local LLM rationalization detection |
Profiles: minimal-stop, balanced, hardened-exec, quality-gate-v2. Apply with lacp claude-hooks apply-profile <profile>.
Biologically-inspired memory consolidation modeled on fungal networks:
| Mechanism | Description |
|---|---|
| Adaptive path reinforcement | Frequently-traversed edges strengthen (like mycelium hyphae) |
| Self-healing | Pruned nodes trigger reconnection of orphaned neighbors |
| Exploratory tendrils | Frontier nodes in active categories shielded from pruning |
| Flow scoring | Betweenness centrality identifies critical knowledge hubs |
| Temporal decay | FSRS dual-strength model with forgetting curve |
# dmux-style multi-instance launch
lacp up --session dev --instances 3 --command "claude"
# Git worktree isolation
lacp worktree create --repo-root . --name "feature-a" --base HEAD
# Batch swarm execution
lacp swarm launch --manifest ./swarm.json
Generate machine-verifiable evidence for PR gates:
lacp e2e smoke --workdir . --init-template --command "npx playwright test --grep @smoke"
lacp api-e2e smoke --workdir . --init-template --command "npx schemathesis run --checks all"
lacp contract-e2e smoke --workdir . --init-template --command "forge test -vv"
lacp pr-preflight --changed-files ./changed-files.txt --checks-json ./checks.json

| Required | Recommended |
|---|---|
bash, python3, jq, rg (ripgrep) | shellcheck, tmux, gh |
The installer auto-detects and installs missing dependencies on macOS via Homebrew.
brew tap 0xNyk/lacp
brew install lacp # published v0.6.0 release
brew install --HEAD lacp # current main, version 0.10.0
curl -fsSLo /tmp/lacp-install.sh \
https://raw.githubusercontent.com/0xNyk/lacp/v0.6.0/install.sh
LACP_REF=v0.6.0 bash /tmp/lacp-install.sh
Change both references to main only when you intend to install unreleased development
code. The script also accepts --dir, --profile, and --with-verify; run it with
--help before installation to see the full contract.
LACP is for developers who need reproducible local agent runs with explicit pass/fail gates and artifacts that can be inspected after execution.
It is a poor fit when you want a managed cloud service, a chat UI, or a setup with no local policy and configuration to maintain.
lacp test --quick # Fast smoke tests
lacp test --isolated # Full isolated suite
lacp doctor --json # Structured diagnostics
lacp posture --strict # Policy compliance check
scripts/ci/test-route-policy.sh
scripts/ci/test-mode-and-gates.sh
scripts/ci/test-knowledge-doctor.sh
scripts/ci/test-ops-commands.sh
scripts/ci/test-install.sh
scripts/ci/test-system-health.sh
scripts/ci/test-obsidian-cli.sh
scripts/ci/test-brain-memory.sh
scripts/ci/smoke.sh
| Command | Purpose |
|---|---|
lacp bootstrap-system | One-command install + onboard + verify |
lacp doctor | Structured diagnostics (--json, --fix-hints, --check-limits) |
lacp status | Current operating state snapshot |
lacp mode | Switch local-only / remote-enabled |
lacp run | Single gated command execution |
lacp loop | Intent โ execute โ observe โ adapt control loop |
lacp test | Local test suite (--quick, --isolated) |
| Command | Purpose |
|---|---|
lacp brain-stack | Initialize/audit 5-layer memory stack |
lacp brain-ingest | Ingest text/audio/video/URLs into Obsidian |
lacp brain-expand | Full brain expansion loop |
lacp brain-doctor | Memory-system health checks |
lacp obsidian | Vault config management (audit/apply/optimize) |
lacp repo-research-sync | Mirror repo research into knowledge graph |
| Command | Purpose |
|---|---|
lacp up | dmux-style multi-instance launch |
lacp orchestrate | dmux/tmux/worktree orchestration adapter |
lacp worktree | Git worktree lifecycle management |
lacp swarm | Batch swarm workflow (plan/launch/status) |
lacp adopt-local | Install LACP routing wrappers for claude/codex |
| Command | Purpose |
|---|---|
lacp route | Deterministic tier/provider routing |
lacp sandbox-run | Gated execution with artifact logging |
lacp policy-pack | Apply policy baselines (starter/strict/enterprise) |
lacp claude-hooks | Audit/repair/optimize hook profiles |
lacp security-hygiene | Secret/path/workflow/.env scan |
lacp pr-preflight | PR policy gate evaluation |
| Command | Purpose |
|---|---|
lacp release-prepare | Pre-live discipline (gate + canary + status) |
lacp release-verify | Release verification (checksum + archive + brew) |
lacp e2e | Browser e2e evidence pipeline |
lacp api-e2e | API/backend e2e evidence pipeline |
lacp contract-e2e | Smart-contract e2e evidence pipeline |
lacp canary | 7-day promotion gate over retrieval benchmarks |
| Command | Purpose |
|---|---|
lacp console | Interactive slash-command shell |
lacp time | Project/client session time tracking |
lacp agent-id | Persistent agent identity registry |
lacp provenance | Cryptographic session provenance chain |
lacp context-profile | Reusable context contract templates |
lacp vendor-watch | Monitor Claude/Codex version drift |
lacp system-health | macOS/Apple Silicon workstation readiness |
lacp mcp-health | Probe all configured MCP servers |
.envLACP_NO_EXTERNAL_CI=true)LACP_ALLOW_EXTERNAL_REMOTE=false)Contributions welcome. See CONTRIBUTING.md for guidelines.
If LACP helps your work, sponsor its continued maintenance.
Solana: 2k1oq9U99mwy4gm8P2hXPJoZusoXQCpFs35EEf5Ve73y
Need agent infrastructure, trading systems, or Solana applications built for your team?
Builderz ships production AI systems across 32+ products in 15 countries.
Get in touch | Nyk | @nykdotdev
Quiet commercial paths from nyk.dev โ same operator, fixed scope:
.claude-plugin/
marketplace.json
.github/
FUNDING.yml
workflows-disabled/
ci.yml
README.md
release.yml
.gitignore
AGENTS.md
automation/
scripts/
active_recall_probes.py
agent_messaging.py
append_agent_daily_activity.py
append_journal_entry.py
apply_pruning.py
archive_inbox.py
audit_agent_system_layout.py
benchmark_memory_retrieval.py
benchmark_memory_trends.py
brain-ingest.sh
build_memory_rag_index.py
capture_snapshot.py
capture_web_research.sh
cleanup_registry_orphans.py
compile_wiki.py
consolidate_research.py
consolidation_lock.py
curate_titles.py
detect_knowledge_gaps.py
DIRECTIVE.md
ensure_obsidian_graph_health.py
extract_sessions.py
extract_shared_memory.py
fetch_x_bookmarks.sh
generate_review_queue.py
index.md
ingest_siftly.py
ingest_video.py
ingest_x_research.py
load_profile.py
load_team.py
manage_knowledge_launchagents.sh
materialize_research_inbox.py
memory_consolidation.py
memory_index_guard.py
memory_ops_policy.py
memory_rag_lib.py
migrate_sites_to_work.py
normalize_builderz_clients.py
optimize_archived_space.py
optimize_obsidian_config.py
process_x_bookmarks.py
provider_router.py
prune_agent_quarantine.py
query_memory_rag.py
recalibrate_memory_benchmark_thresholds.py
recommend_pruning.py
render_html.py
render_mcp_memory.py
render_skill_index.py
route_inbox.py
run_agent_system_hygiene.sh
run_brain_expand_6h.sh
run_brain_expand.sh
run_memory_benchmark_suite.sh
run_memory_benchmark.sh
run_memory_pipeline.sh
run_memory_threshold_recalibration.sh
run_phase2b.sh
run_quarantine_maintenance.sh
run_repo_research_sync.sh
run_research_promotions.sh
run_session_sync.sh
run_shared_memory.sh
run_snapshot.sh
run_weekly_maintenance.sh
run_x_bookmark_pipeline.sh
semantic_dedup.py
suggest_memory_promotions.py
suggest_research_promotions.py
sync_agent_daily_from_runs.py
sync_agent_daily_knowledge.py
sync_agent_session_history.py
sync_article_memory.py
sync_repo_knowledge.py
sync_research_knowledge.py
vault_hygiene.sh
voice_daily_note.py
voice.sh
watch_dashboard.py
xint-brain-ingest.sh
autoresearch/
evaluate_memory.py
evaluate.py
last_eval_memory.json
last_eval.json
optimize.py
program.md
results.tsv
bin/
lacp
lacp-adopt-local
lacp-agent-id
lacp-api-e2e
lacp-auth
lacp-auto-rollback
lacp-automations-tui
lacp-bootstrap
lacp-bootstrap-system
lacp-brain
lacp-brain-doctor
lacp-brain-expand
lacp-brain-ingest
lacp-brain-nightly
lacp-brain-promote
lacp-brain-resolve
lacp-brain-stack
lacp-browser-evidence-validate
lacp-cache-audit
lacp-cache-guard
lacp-canary
lacp-canary-optimize
lacp-capability-gaps
lacp-claude-hooks
lacp-console
lacp-context
lacp-context-profile
lacp-contract-e2e
lacp-credential-profile
lacp-curate
lacp-doctor
lacp-e2e
lacp-eval
lacp-focus
lacp-handoff
lacp-harness-replay
lacp-harness-run
lacp-harness-validate
lacp-health-snapshot
lacp-incident-drill
lacp-install
lacp-knowledge-doctor
lacp-learn-capture
lacp-learn-eval
lacp-learn-promote
lacp-learn-retrieve
lacp-learn-rollback
lacp-lessons
lacp-loop
lacp-loop-profile
lacp-mcp-health
lacp-mcp-profile
lacp-memory-kpi
lacp-migrate
lacp-mode
lacp-obsidian
lacp-obsidian-cli
lacp-obsidian-memory-optimize
lacp-onboard
lacp-open-source-check
lacp-optimize-loop
lacp-orchestrate
lacp-policy-pack
lacp-posture
lacp-pr-preflight
lacp-provenance
lacp-reflect
lacp-release-gate
lacp-release-prepare
lacp-release-publish
lacp-release-verify
lacp-remote-setup
lacp-remote-smoke
lacp-repo-research-sync
lacp-report
lacp-repos-index
lacp-research
lacp-route
lacp-runs
lacp-sandbox-run
lacp-scaffold-audit
lacp-schedule-health
lacp-security-hygiene
lacp-session-fingerprint
lacp-skill-audit
lacp-skill-factory
lacp-skill-score
lacp-skill-sync-anthropic
lacp-sms
lacp-status-report
lacp-stream
lacp-swarm
lacp-system-health
lacp-test
lacp-time
lacp-tools
lacp-trace-triage
lacp-tui
lacp-unadopt-local
lacp-up
lacp-vendor-watch
lacp-verify
lacp-watch
lacp-workflow-run
lacp-worktree
CHANGELOG.md
CLAUDE.md
config/
autoresearch-program.md
capability-gaps.json
consolidation.json
context-modes/
brainstorm.md
debugging.md
handoff-resume.md
implementation.md
orchestrate.md
review.md
sprint.md
tdd.md
think.md
thinking-partner.md
verification.md
context-profiles.json
credential-profiles.json
harness/
api-e2e-flows.example.json
browser-evidence.schema.json
contract-e2e-flows.example.json
e2e-flows.example.json
sandbox-profiles.yaml
tasks.schema.json
verification-policy.yaml
lacp-brain-nightly.cron
lacp.env.example
learning/
learning-events.schema.json
promotion-policy.json
loop-profiles.json
mcp-auth-policy.json
mcp-profiles.json
memory/
node-schema.json
obsidian/
manifest.json
optimization-profiles.json
plugin-settings.json
policy-packs/
enterprise.json
starter.json
strict.json
profiles/
default.yaml
prompt-prefixes.json
research/
surfaces.json
risk-policy-contract.json
risk-policy-contract.schema.json
sandbox-policy.json
skins/
cyberpunk.yaml
default.yaml
system-health-policy.json
teams/
default.yaml
heterogeneous.yaml
research.yaml
CONTRIBUTING.md
docs/
assets/
.gitkeep
evidence-recovery-loop.jpeg
execution-contract.jpeg
github-social.png
host-boundary.jpeg
lacp-control-plane.jpeg
readme-banner.png
risk-tier-routing.jpeg
clipper-autonomous-knowledge-loop.md
demos/
council-next-steps-demo.md
entity-id-convention.md
framework-scope.md
implementation-path-2026.md
incident-response.md
learning-loop-go-no-go-template.md
local-dev-loop.md
memory-quality-workflow.md
multi-vault-multi-hop-reasoning-spec.md
obsidian-frontmatter-migration-playbook.md
optimization-audit-2026-02-20.md
plans/
2026-04-13-cross-cli-learning-control-plane.dag.json
2026-04-13-cross-cli-learning-control-plane.md
2026-04-14-learning-loop-7day-checklist.md
readme-banner-prompt.md
release-checklist.md
releases/
v0.2.0.md
research/
dmux-integration-2026-02-21.md
harness-engineering-2026-02-21.md
llm-debugging-robustness-notes-2026-03-23.md
runbook.md
troubleshooting.md
Formula/
lacp.rb
Heartbeat.md
hooks/
detect_session_changes.py
eval_checkpoint.py
extract_memories.py
hook_contracts.py
hook_telemetry.py
pretool_guard.py
self_memory_system.py
session_orient.sh
session_start.py
stop_quality_gate.py
stop_quality_gate.sh
test_stop_hook.py
thinking_nudge.py
write_validate.py
install.sh
LICENSE
Memory/
context/
README.md
glossary.md
people/
README.md
projects/
README.md
README.md
plugin/
.claude-plugin/
marketplace.json
plugin.json
commands/
hardening-status.md
hooks/
hooks.json
scripts/
detect_session_changes.py
eval_checkpoint.py
hook_contracts.py
hook_telemetry.py
pretool_guard.py
self_memory_system.py
session_start.py
stop_quality_gate.py
thinking_nudge.py
skills/
context-modes/
brainstorm.md
debugging.md
handoff-resume.md
implementation.md
orchestrate.md
review.md
SKILL.md
sprint.md
tdd.md
think.md
thinking-partner.md
verification.md
quality-gate/
SKILL.md
session-hardening/
SKILL.md
README.md
scripts/
archive_inbox.py
brain_utils.py
ci/
security-hygiene-audit.sh
smoke.sh
test-adopt-local.sh
test-agent-id.sh
test-api-e2e.sh
test-auto-deps.sh
test-auto-rollback.sh
test-automations-tui.sh
test-blind-spot.sh
test-bootstrap-system.sh
test-brain-automation-scripts.sh
test-brain-doctor.sh
test-brain-expand-parallel.sh
test-brain-expand.sh
test-brain-ingest.sh
test-brain-memory.sh
test-brain-promote.sh
test-brain-stack.sh
test-browser-evidence-validate.sh
test-cache-audit.sh
test-cache-guard.sh
test-canary-baseline.sh
test-canary-optimize.sh
... 113 moreLocal-first X Intelligence CLI for search, monitoring, analysis, exports, OAuth actions, and agent tooling.
FAQ
lacp is a Claude Code plugin with 3 hand-picked skills for security work, indexed on Flowy. Install it with the command on its page. It includes context-modes, quality-gate, session-hardening. Its skills do not fire on their own yet. Request auto-invocation to have Flowy route them as you prompt. Free and open source.