Local context compiler
One AGENTS.md. Every coding agent.
Stop maintaining the same project rules in .cursorrules, CLAUDE.md, and copilot-instructions.md. Write them once in AGENTS.md — terso compiles the rest.
Open source · MIT · Free while in beta
The problem
You open Claude Code on a project you haven't touched in 3 weeks. It knows nothing — your architecture decisions, the bug you fixed, why you chose Supabase over Firebase. You re-explain everything. Again.
Your knowledge is scattered across chat histories, random docs, and your head. Every new session starts from zero.
Terso fixes this.
How it works
Edit one file. Compile the rest.
You run this
Your agents read these
Capabilities
Capture from anywhere.
Voice notes from Telegram, quick thoughts from the CLI, pastes from the web, GitHub webhooks, forwarded emails. Under 3 seconds to capture a thought. Zero friction, zero context switching.
Secrets scanned before any LLM.
Deterministic regex scanning runs before any AI model sees your input. API keys, tokens, passwords, and connection strings are stripped and replaced with [REDACTED:type] markers. The originals are stored encrypted in a local vault.
Processing pipeline
Files, not APIs.
No MCP servers to install, no auth to wire up, no runtime API calls. Terso compiles your AGENTS.md into the native config files each agent already reads. Cursor reads .cursorrules. Claude Code reads CLAUDE.md. Copilot reads .github/copilot-instructions.md. Same instructions, three places, one source.
More
Offline mode
Capture locally when offline. Sync when you reconnect. Nothing is lost.
Secret scanning
Deterministic regex before any LLM call. API keys, tokens, passwords stripped automatically.
Confidence routing
High confidence auto-promotes. Low confidence holds for review. Junk expires and self-cleans.
Shared ops
Cross-project standards compiled once, synced to every repo. Deploy recipes, coding standards, service inventory.
Review budget
Maximum 20 items per week. Overflow auto-archives. Your attention is protected.
Cost tracking
Every LLM call logged with model, tokens, cost, and project. $15/day cap enforced.