Observal(4k stars): Coding agent resource registry with privacy preserving usage analytics
What it does
All text below is quoted directly from the project README.
>Observal is the control plane and system of record for internal coding agent resources. Every tech-forward organization today creates internal Skills, Agents files, MCP clients. Though the creation of these coding agent resources has been prolific, peer adoption and usage is sparse. Coding agent users today end up creating their own version of such resouces without reusing existing packages.
Why teams use Observal:
- Centralize resources in one platform: Store Skills, MCP clients, hooks, prompts, agent files, and sandboxes in a single registry.
- Faster Onboarding: By storing enterprise context for coding agents, teams can onboard colleagues faster and reduce TTF contribution.
- Run a governed registry: Review submissions, approve internal agents, inspect version diffs, and give developers one trusted place to install from.
- Render across multiple Coding IDE/CLI: Generate the correct config for each supported harness instead of maintaining separate setup instructions for every harness.
- Let agents use each other: Every approved resource is discoverable over the open ARD standard, and a running agent can hand part of its task to another approved agent, whether it lives in the registry or is a remote A2A service.
- Learn what works: Use real adoption and session data to see which agents, tools, prompts, and workflows help teams. Insights populate what is needed automatically.
- Replay sessions when needed: Use traces as evidence for debugging, review, audits, and deeper analysis.
Current Capabilities:
- Coding Agents can auto-discover and install resources with harness compatibility badges using ARD
- Supported resources: Agent files, MCP clients, Skills, Hooks, Prompts, Sandboxes
- AI-powered insight reports analyze usage patterns across all sessions, what's working, what's hindering, and quick wins.
- Full session overview with token counts, models, tools, and turn-by-turn timeline
- Admin review queue with full prompt inspection and approve/reject
- Side-by-side version diffs before approving a new release
- The Apache-2.0 distribution includes audit logs, SAML SSO, and SCIM provisioning.
Repository
Observal/Observal
> Observal solves this by providing a centralized discovery layer for coding agent resources, along with insights into usage patterns. It turns silent failures into actionable feedback, ensuring internal resources are continuously optimized for users.
Repository stats
|Metric|Value|
|:-|:-|
|||
|Stars|4,363|
|Forks|1,133|
|Last release|v1.14.0 (Oct 4, 2026)|
|Languages|Python 80.3%, TypeScript 16.2%, HCL 1.9%|
|Contributors|65|
|AI contributor accounts (Claude / Codex / Cursor / Copilot)|Claude, Cursor|
|AI co-authored commits|17 (Claude: 11, Cursor: 6)|
Main contributor
|Field|Value|
|:-|:-|
|||
|Name|Hari Srinivasan|
|GitHub|github.com/Haz3-jolt|
|Commits to this repo|1,171 (top contributor)|
|Company / Location|Observal Inc, Dover|
|Followers|62|
|Public repos|44|
|On GitHub since|Feb 2021|
6 points · 3 comments
Mentions
Observal(4k stars): Coding agent resource registry with privacy preserving usage analytics What it does All text below is quoted directly from the project README. >Observal is the control plane and system of record for internal coding agent resources. Every tech-forward organization today creates internal Skills, Agents files, MCP clients. Though the creation of these coding agent resources has been prolific, peer adoption and usage is sparse. Coding agent users today end up creating their own version of such resouces without reusing existing packages. Why teams use Observal: - Centralize resources in one platform: Store Skills, MCP clients, hooks, prompts, agent files, and sandboxes in a single registry. - Faster Onboarding: By storing enterprise context for coding agents, teams can onboard colleagues faster and reduce TTF contribution. - Run a governed registry: Review submissions, approve internal agents, inspect version diffs, and give developers one trusted place to install from. - Render across multiple Coding IDE/CLI: Generate the correct config for each supported harness instead of maintaining separate setup instructions for every harness. - Let agents use each other: Every approved resource is discoverable over the open ARD standard, and a running agent can hand part of its task to another approved agent, whether it lives in the registry or is a remote A2A service. - Learn what works: Use real adoption and session data to see which agents, tools, prompts, and workflows help teams. Insights populate what is needed automatically. - Replay sessions when needed: Use traces as evidence for debugging, review, audits, and deeper analysis. Current Capabilities: - Coding Agents can auto-discover and install resources with harness compatibility badges using ARD - Supported resources: Agent files, MCP clients, Skills, Hooks, Prompts, Sandboxes - AI-powered insight reports analyze usage patterns across all sessions, what's working, what's hindering, and quick wins. - Full session overview with token counts, models, tools, and turn-by-turn timeline - Admin review queue with full prompt inspection and approve/reject - Side-by-side version diffs before approving a new release - The Apache-2.0 distribution includes audit logs, SAML SSO, and SCIM provisioning. Repository Observal/Observal > Observal solves this by providing a centralized discovery layer for coding agent resources, along with insights into usage patterns. It turns silent failures into actionable feedback, ensuring internal resources are continuously optimized for users. Repository stats |Metric|Value| |:-|:-| ||| |Stars|4,363| |Forks|1,133| |Last release|v1.14.0 (Oct 4, 2026)| |Languages|Python 80.3%, TypeScript 16.2%, HCL 1.9%| |Contributors|65| |AI contributor accounts (Claude / Codex / Cursor / Copilot)|Claude, Cursor| |AI co-authored commits|17 (Claude: 11, Cursor: 6)| Main contributor |Field|Value| |:-|:-| ||| |Name|Hari Srinivasan| |GitHub|github.com/Haz3-jolt| |Commits to this repo|1,171 (top contributor)| |Company / Location|Observal Inc, Dover| |Followers|62| |Public repos|44| |On GitHub since|Feb 2021|