Preview. These maps are our reading of public sources and haven't been checked with the projects' maintainers yet.
grith
Linux syscall-level supervisor for coding agents: every file read, command, network call and process spawn is scored; low scores run, high scores are denied, the middle is frozen for a person to approve.
grith.ai/Active
v0.3.4 released 2026-09-03; repo pushed 2026-10-18 (exported per release from a private monorepo). (checked 2026-10-25)
In Agent guardrails
Where it stands apart
- How is the main thing licensed? copyleft or source-available with restrictions (10% of 21 others)
- Which shared standard or format does it mainly build on? OS sandbox primitives (Seatbelt, bubblewrap, Linux namespaces, seccomp) (14% of 21 others)
- Does it control the agent's outbound network access? yes, but open by default or optional (25% of 16 others)
What it shares with most of the community
- Is it actively maintained? active (81% of 21 others)
- How is it mainly sustained? company with a paid product, tier, or ads (50% of 20 others)
- Can it run entirely on your own device or infrastructure, without the maker's servers? yes (76% of 21 others)
- Do you need an account to use it? no account (67% of 21 others)
- Who is it for? developers (90% of 21 others)
- What mainly decides whether an action is allowed? rules, policy, or boundaries written in advance (57% of 21 others)
- If the guard itself breaks, is missing, or cannot decide, what happens by default? fails closed: the action does not run (71% of 17 others)
- Which agents does it work with? any agent or process (not limited to a named list) (71% of 21 others)
- In the default setup, where does the agent's work actually execute? directly on the host machine, as usual (52% of 21 others)
- What is the main thing it protects? the developer's machine and files (52% of 21 others)
- What is it mainly for? adding checkpoints, review, or evidence (52% of 21 others)
- Is enforcement kept out of the agent's reach? yes, enforced in code or infrastructure the agent cannot change (95% of 21 others)
Nearest neighbors
- Plimsoll 73% of 15 shared answers match
- Drop 71% of 17 shared answers match
- Vultrino 71% of 17 shared answers match
Every answer
| Question | Answer | Source |
|---|---|---|
| Is it actively maintained? | active | source 2026-10-25 |
| How is the main thing licensed? | stands apart copyleft or source-available with restrictions MPL-2.0; Pro/Enterprise features in the same binary unlocked by signed licences. | source 2026-10-25 |
| How is it mainly sustained? | company with a paid product, tier, or ads Free tier offline; paid tiers. | source 2026-10-25 |
| Can it run entirely on your own device or infrastructure, without the maker's servers? | yes | source 2026-10-25 |
| Do you need an account to use it? | no account Docs: free tier runs entirely offline, no account, no telemetry. | source 2026-10-26 |
| Who is it for? | developers | source 2026-10-25 |
| Which shared standard or format does it mainly build on? | stands apart OS sandbox primitives (Seatbelt, bubblewrap, Linux namespaces, seccomp) Syscall-level supervision on Linux. | source 2026-10-26 |
| Where does it mainly step in? | at the OS or VM boundary (sandbox, container, syscall supervisor) | source 2026-10-25 |
| What mainly decides whether an action is allowed? | rules, policy, or boundaries written in advance Deterministic scoring rules decide most calls; ambiguous ones (score 3-8) wait for a person. | source 2026-10-25 |
| If the guard itself breaks, is missing, or cannot decide, what happens by default? | fails closed: the action does not run 'Nothing runs on a maybe'; non-interactive sessions 'fail safe and deny'. | source 2026-10-25 |
| Which agents does it work with? | any agent or process (not limited to a named list) grith exec <agent>; profiles for Claude Code, Codex, Aider, Cursor and others. | source 2026-10-25 |
| In the default setup, where does the agent's work actually execute? | directly on the host machine, as usual Supervised, not isolated. | source 2026-10-25 |
| What is the main thing it protects? | the developer's machine and files | source 2026-10-25 |
| Does it keep a record of agent actions? | yes, ordinary logs or a timeline Local SQLite audit log. | source 2026-10-25 |
| Does it control the agent's outbound network access? | stands apart yes, but open by default or optional Network calls are scored like other syscalls. | source 2026-10-25 |
| What is it mainly for? | adding checkpoints, review, or evidence | source 2026-10-25 |
| Is enforcement kept out of the agent's reach? | yes, enforced in code or infrastructure the agent cannot change | source 2026-10-25 |
Sources
This page was derived from:
- GitHub · github.com/grith-ai/grith · read 2026-10-25
- Web page · grith.ai/ · read 2026-10-25
Are you a maintainer? Claiming and correcting projects is coming soon.