Preview. These maps are our reading of public sources and haven't been checked with the projects' maintainers yet.
Conduct
Governance control plane for agents: one signed policy decides block/warn/audit/inject for every LLM call, shell tool and MCP call across Claude Code, Cursor, Copilot and Codex, with a hash-chained audit trail.
conductai.ai/Active
booster/v0.8.1 released 2026-10-12; repo pushed 2026-10-19; Show HN 22 points. (checked 2026-10-25)
In Agent guardrails
Where it stands apart
- Do you need an account to use it? account required (24% of 21 others)
- Which shared standard or format does it mainly build on? OpenAI- or Anthropic-compatible LLM API (base-URL proxy) (5% of 21 others)
- What is the main thing it protects? outside systems and data (APIs, databases, money, private records) (19% of 21 others)
- Does it keep a record of agent actions? yes, tamper-evident (signed or hash-chained) (10% of 20 others)
What it shares with most of the community
- Is it actively maintained? active (81% of 21 others)
- How is the main thing licensed? permissive open source (MIT/Apache/BSD) (67% 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)
- 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)
- Does it control the agent's outbound network access? no (56% of 16 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
- Invariant Guardrails 81% of 16 shared answers match
- cMCP (AgenTrust) 80% of 15 shared answers match
- OpenAPPA 80% of 15 shared answers match
Every answer
| Question | Answer | Source |
|---|---|---|
| Is it actively maintained? | active | source 2026-10-25 |
| How is the main thing licensed? | permissive open source (MIT/Apache/BSD) Apache-2.0 | source 2026-10-25 |
| How is it mainly sustained? | company with a paid product, tier, or ads Hosted workspace with trial; self-host also offered. | source 2026-10-25 |
| Can it run entirely on your own device or infrastructure, without the maker's servers? | yes docker compose self-host. | source 2026-10-25 |
| Do you need an account to use it? | stands apart account required Hosted workspace with Sign in (Free tier up to 3 agents); self-host only on Enterprise. | source 2026-10-26 |
| Who is it for? | developers Engineering teams and security/compliance. | source 2026-10-25 |
| Which shared standard or format does it mainly build on? | stands apart OpenAI- or Anthropic-compatible LLM API (base-URL proxy) Map note: LLM router via base-URL proxy, plus guards on shell and MCP calls. | source 2026-10-26 |
| Where does it mainly step in? | at the tool-call, MCP, or API layer (proxy or gateway) LLM router plus guard on shell and MCP calls. | source 2026-10-25 |
| What mainly decides whether an action is allowed? | rules, policy, or boundaries written in advance | 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 README: failure mode 'Fail-closed'. | source 2026-10-25 |
| Which agents does it work with? | any agent or process (not limited to a named list) Enforces across any MCP-compatible agent plus drop-in base-URL proxy; not limited to a named list. | source 2026-10-26 |
| In the default setup, where does the agent's work actually execute? | directly on the host machine, as usual | source 2026-10-25 |
| What is the main thing it protects? | stands apart outside systems and data (APIs, databases, money, private records) | source 2026-10-25 |
| Does it keep a record of agent actions? | stands apart yes, tamper-evident (signed or hash-chained) SHA-256 hash chain; signed policy. | source 2026-10-25 |
| Does it control the agent's outbound network access? | no | 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/sseshachala/conductai · read 2026-10-25
- Web page · conductai.ai/ · read 2026-10-25
Are you a maintainer? Claiming and correcting projects is coming soon.