Journeys
Journeys
Twenty-three code-grounded journeys, grouped into four persona tracks. Every CLI command and MCP tool appears in at least one — start at the track that sounds like you and follow it end to end.
Get Started
From zero to compressed reads in ten minutes — auto-detected for your editor.
Daily Workflow
Compressed reads, persistent memory and smart routing on every turn.
Daily Use
Compressed reads, search and shell output on every turn — invisibly.
Memory & Knowledge
Sessions, knowledge and checkpoints that auto-restore — never re-explain.
Code Intelligence
Call graphs, impact analysis and repo maps across 18 languages.
Context Engineering & Observability
Radar, control, compile and ledger for hands-on window management.
Analytics, Insights & Reporting
Gain, token reports, dashboards and CEP to prove the payoff.
Beyond Coding: Web & Research
Pull the web, PDFs and YouTube into context as compressed, cited evidence.
Context Firewall
Runaway tool output becomes a compact digest plus a zero-loss retrieval ref.
Scale & Teams
Shared memory, providers and a team server — one brain across many agents.
Proxy & Power Integrations
Compress the LLM stream itself, serve over HTTP, and wire in external providers.
Multi-Agent Collaboration
Shared memory, handoffs and diaries across many agents.
Team, Cloud & Self-Hosting
One governed context server for the whole org — self-hosted, role-scoped, local stays free.
Multi-Repo Workspaces
Auto-detect, extra_roots and graph indexing across independent repos.
MCP Tool-Catalog Gateway
Unlimited downstream MCP tools at a flat, constant context cost.
Build Your Own Agent: SDKs & /v1 API
Embed LeanCTX in your own harness over a stable, discoverable /v1 contract.
Context Personas
One switch reshapes the whole context surface for your domain.
Universal Intake: Docs, Data & Email
Index any corpus — not just code — with format-aware extractors.
Extend Without Forking: Plugins & WASM
Add tools, compressors and providers as sandboxed plugins or WASM — no fork.
Operate & Govern
Security, roles, budgets and performance tuning for real codebases.
Lifecycle & Troubleshooting
The symptom → fix playbook, plus update, cache and uninstall done cleanly.
Customization & Governance
Profiles, roles, rules and hardening to shape every tool call.
Security & Governance
PathJail, shell allowlist, secret detection and role policies.
Performance Tuning
Memory profiles, cache caps and limits for big repos.
Prove It: Savings, Quality & Benchmarks
Three signed, offline-verifiable proofs: the savings receipt, the with/without quality verdict, and the reproducible scorecard.
Per-item Sensitivity Floor
Redact or drop sensitive items before anything reaches the model.