Show HN: Grinta – a local-first coding agent built for long autonomous runs

Developer Youssef Mejdi released Grinta v1.0.0-rc1, a local-first, provider-agnostic coding agent for long autonomous runs that integrates with LSP and DAP. The tool runs entirely on the user's machine without cloud dependency, supports multiple AI model providers, and includes safety rails and durable session management. It is available for Linux, Windows, and macOS via pipx.

Local-first. Provider-agnostic. Ships with real LSP + DAP. Optional extras stay opt-in.A terminal coding agent that plans, executes, validates, and finishes — without a cloud control plane, without lock-in to one model vendor, and without the old heavyweight install footprint. Current status: v1.0.0-rc1 public release candidate. Linux, Windows, and macOS run required unit and extended CI gates; smoke-install and onboarding validation are in place. Remaining GA work is mostly documentation alignment, contributor-doc honesty, and edge-case hardening after the post-rc1 decomposition wave. Created and maintained by Youssef Mejdi https://github.com/josephsenior . Direct link if the video does not load: docs/assets/grinta-demo.mp4 /josephsenior/Grinta-Coding-Agent/blob/main/docs/assets/grinta-demo.mp4 . - Latest public build is v1.0.0-rc1 release candidate , not final GA. - Required CI covers sharded Linux unit coverage 75% , cross-platform unit gates, and integration/e2e/stress on Linux, Windows, and macOS; smoke-install and onboarding validation are in place for the current release line. - We are actively collecting feedback on UX clarity and edge-case reliability before the GA call. - Linux, Windows, and macOS are supported release targets, but certification depth differs by platform; see docs/SUPPORT MATRIX.md /josephsenior/Grinta-Coding-Agent/blob/main/docs/SUPPORT MATRIX.md . - If you hit friction, please open an issue with the RC Feedback template from the issue chooser. - GA criteria and release gate details live in docs/RELEASE CHECKLIST.md /josephsenior/Grinta-Coding-Agent/blob/main/docs/RELEASE CHECKLIST.md . Grinta distinguishes itself by focusing on a completely local-first, provider-agnostic, and deeply integrated terminal workflow. Unlike thin wrappers or cloud-dependent control planes, Grinta: Local-first : Grinta’s control plane, execution, storage, and session history run locally. Model inference may be local or remote depending on the configured provider. Provider-agnostic : Connects seamlessly with OpenAI, Anthropic, Google, OpenRouter, Ollama, or LM Studio using a unified interface. Deep tooling integration : Automatically discovers and integrates with local Language Servers LSP and Debug Adapters DAP on your PATH. Built-in safety rails : Classifies actions by risk, implements confirmation gates, and masks secrets in console outputs. Durable long sessions : Built with an event-stream ledger supporting automatic compaction, manual checkpoints, and easy reverts. Consumer, dev, Windows, WSL2, Linux, macOS: docs/QUICK START.md /josephsenior/Grinta-Coding-Agent/blob/main/docs/QUICK START.md pipx install grinta consumer — then cd "<project " && grinta Optional extras: pipx install "grinta rag " · "grinta browser " · "grinta all " — details in Quick Start /josephsenior/Grinta-Coding-Agent/blob/main/docs/QUICK START.md . Task completion, not just file edits. Stuck detection, recovery directives, and optional completion-quality validation help reduce premature "done". Model-agnostic. OpenAI, Anthropic, Google, OpenRouter, Ollama, LM Studio — same prompt surface, same tools. Local-first. Code stays in your workspace; sessions, checkpoints, and audit logs live under ~/.grinta/workspaces/<id /storage . Strong safety rails. Risk-classified actions, CRITICAL refusal gate, secret masking, and a session-wide audit trail. Durable long sessions. Event-stream ledger, automatic compaction, manual /checkpoint , and revert. Terminal UI. Interactive TTY sessions launch the Textual app with HUD, transcript cards, settings/sessions dialogs, and slash commands; piped input uses a non-interactive fallback. Grinta exposes three modes in the Textual HUD Chat, Plan, Agent . They change the conversational contract, not just the prompt tone: Chat — read-only Q&A and discovery tools; no edits or shell. Plan — read-only investigation; may use task tracker for a structured plan when enabled, or prose only. Switch to Agent mode to execute. Agent — full task loop default for direct work . Autonomy /autonomy : conservative, balanced, full controls confirmation prompts in Agent mode only. Runtime hardening is configured separately with security.execution profile standard is the default and supports the interactive terminal and debugger; hardened local and sandboxed local add stricter policy gates . | Command | What it does | |---|---| /help | Full slash-command reference | /settings | Model, API key, and MCP configuration | /sessions | List past sessions; /resume <N|id to continue one | /model | Show or switch the active provider/model | /mode | View or set interaction mode chat / plan / agent | /autonomy | View or set confirmation behavior | /cost | Tokens, calls, USD spent this session | /diff | Workspace git changes --stat , --name-only , --patch | /health | Fast self-check for debug adapters, ripgrep, git, and model setup | /checkpoint | Snapshot the workspace revertable | /status | HUD snapshot; /status verbose adds diagnostics | /compact | Force context compaction now | Playbook workflows /debug , /testing , /feature , … and the full registry are in /help . Grinta executes actions on the local host. The default standard profile preserves full interactive terminal and debugger support. hardened local adds stricter policy checks but is not sandboxing or process isolation; sandboxed local adds process isolation only for non-interactive commands. Read docs/SECURITY CHECKLIST.md /josephsenior/Grinta-Coding-Agent/blob/main/docs/SECURITY CHECKLIST.md before pointing Grinta at code you do not trust — for hostile codebases, run inside a VM or container. Grinta is evaluated through recorded long-horizon autonomous sessions and forensic event-stream audits. A recent full-autonomy run: - executed for 4h 33m - processed 16,393 events - recorded 373 tool outcomes — 368 successful, 5 failed - produced 123 file events - recovered through inference-provider connection failures - detected process suspension without misclassifying it as an agent hang - rejected malformed model tool payloads at the tool boundary - handled context pressure during execution - reached the final FINISHED state The audit recorded one initial user turn and no subsequent user turns during execution. 📊 Read the sanitized autonomous execution report /josephsenior/Grinta-Coding-Agent/blob/main/docs/evidence/2026-07-09-autonomous-run-report.md Full forensic session audits are retained privately. php graph TB User User -- CLI CLI: backend.cli.entry CLI -- TUI TTY: Textual TUI CLI -- NonInteractive Piped input: non-interactive runner TUI -- Orch SessionOrchestrator NonInteractive -- Orch Orch -- Engine Engine\nplanning + tool intent Orch -- Pipe Operation pipeline\nsafety + validation Pipe -- Runtime RuntimeExecutor\nlocal execution Runtime -- Obs Observations Obs -- Orch Orch -- Ledger EventStream / durability Orch -- FinishGate Task validation\nbefore finish See docs/ARCHITECTURE.md /josephsenior/Grinta-Coding-Agent/blob/main/docs/ARCHITECTURE.md for the deep dive. Contributors: Linux PR gates shard the unit corpus backend/tests/unit with 75% coverage, then run integration/e2e/stress in extended jobs; Windows and macOS run the same unit corpus plus the extended tier docs/CI.md /josephsenior/Grinta-Coding-Agent/blob/main/docs/CI.md . Match the tier you are changing before opening a PR CONTRIBUTING.md /josephsenior/Grinta-Coding-Agent/blob/main/CONTRIBUTING.md testing-before-a-pull-request . Grinta is a single-author project, written and rewritten in public. The journey — what was killed, what was wrong, what got rebuilt — is The Book of Grinta : start at Preface /josephsenior/Grinta-Coding-Agent/blob/main/docs/journey/preface-why-this-story-matters.md → 00 · Meaning of Grinta /josephsenior/Grinta-Coding-Agent/blob/main/docs/journey/00-the-meaning-of-grinta.md through the numbered chapters to 45 · The Product Surface Became Real /josephsenior/Grinta-Coding-Agent/blob/main/docs/journey/45-the-product-surface-became-real.md and 46 · The Decomposition Wave /josephsenior/Grinta-Coding-Agent/blob/main/docs/journey/46-the-decomposition-wave.md , then the epilogue 07 · The Road Ahead /josephsenior/Grinta-Coding-Agent/blob/main/docs/journey/07-the-road-ahead.md . Full index and act structure: docs/journey/README.md /josephsenior/Grinta-Coding-Agent/blob/main/docs/journey/README.md . Stable shortcut from the repo root: BOOK OF GRINTA.md /josephsenior/Grinta-Coding-Agent/blob/main/BOOK OF GRINTA.md . Use the container image directly no official compose stack in this repo : docker run -it --rm -v "$PWD:/work" -w /work \ -e LLM API KEY=${LLM API KEY} \ ghcr.io/josephsenior/grinta:latest Run grinta first interactive launch runs setup or see docs/SETTINGS.md /josephsenior/Grinta-Coding-Agent/blob/main/docs/SETTINGS.md . Plan - execute - observe - validate - finish. Grinta uses compactor strategies to keep long sessions coherent under context limits. Stuck detection, retry/recovery flows, and circuit breakers are built into orchestration. Optional completion-quality validation surfaces advisory warnings when tracked work looks incomplete; it does not hard-block the agent from finishing. Start here end users : Contributors: More reference: Optional narrative: The Book of Grinta /josephsenior/Grinta-Coding-Agent/blob/main/docs/journey/README.md — engineering memoir; may not reflect the current product surface. See CONTRIBUTING.md /josephsenior/Grinta-Coding-Agent/blob/main/CONTRIBUTING.md . MIT — see LICENSE /josephsenior/Grinta-Coding-Agent/blob/main/LICENSE . Dependency attribution and notice policy: THIRD PARTY NOTICES.md /josephsenior/Grinta-Coding-Agent/blob/main/THIRD PARTY NOTICES.md .