Skip to content
The Daily Repo

Firma-AI / openfirma

Runtime enforcement boundary for AI agents: a local sidecar that gates every outbound call against Cedar policies you own. Deterministic, call-level, no model on the hot path

Why this job: topics: ai-governance, guardrails, ai-safety

Picture from the Firma-AI/openfirma README

What it does

  • Structural interception. every modality of action funnels through the Sidecar, with the kernel sandbox as the floor
  • Deterministic intent. every tool call is classified into an enforceable action class; Cedar evaluates the same input to the same decision, every time
  • Per-call enforcement. policy is evaluated before execution, against current policy and accumulated session state
  • JIT credentials. a federated broker issues credentials per call on ALLOW; the agent never holds raw tokens; exfiltration is structurally impossible
  • Signed audit. every decision emits a signed execution event with the exact envelope the policy saw

Get started

curl -fsSL https://install.openfirma.ai | sh
Maintenance
Active
Last commit 10 days ago
Stars
143
On GitHub
Licence
GPL-3.0
Share-alike terms
Downloads for
3 systems
Mac, Windows, Linux
Latest version
v0.1.6
Released 3 months ago
Built with
Rust
97% of the code

Is it looked after?

Contributors
6
Last 90 days
Issues
0% closed
3 still open
Pull requests
0 merged
0 waiting
Releases
11
11 in the last year

Similar repos

Repos similar to this one
RepoStarsLast commitLicenceDownloads for
microsoft / agent-governance-toolkit6,5442 days agoMITNo downloads
WhitzardAgent / AgentGuard1593 days agoGPL-3.0No downloads
DobermanCore / Doberman-Core24313 days agoApache-2.0No downloads
More: download files, languages, topics and project record

Download files, v0.1.6

  • Mac4 files, 99 downloads
  • Windows4 files, 92 downloads
  • Linux4 files, 97 downloads

All files on GitHub (opens in new tab)

Languages

  • Rust 97%
  • Shell 2%
  • Python <1%
  • JavaScript <1%

Topics

  • access-control
  • agentic-ai
  • ai-agents
  • ai-governance
  • ai-safety
  • authorization
  • cedar
  • cedar-policy
  • guardrails
  • policy-engine
  • runtime-security
  • rust

Project record

  • JobAI security
  • StatusListed
  • Commits1,006
  • Forks8
  • Watching1
  • Stars in 28 days+3
  • CreatedMar 22, 2026
  • First seen by usNov 7, 2026
  • CheckedNov 7, 2026

Type to search.

Try