Live end-to-end fleet remediation on TrueFoundry: Vercel DVIR UI â MCP Gateway (`fleet-demo-mock`) â ChatGPT + Claude + Grok as three harnesses on one governed channel â with approval-gated writes and full traces. Solution: FleetHeal is a production-shaped agent harness, not a chat toy. Inspectors submit defects, including crack-related flags, in a live Vercel UI. TrueFoundry MCP Gateway hosts `fleet-demo-mock` and live-reads the store via FLEETHEAL_API_BASE=https://fleetheal.vercel.app. ChatGPT, Claude, and Grok connect as separate harnesses to the SAME gateway; model choice is swappable while governance stays central. Read tools (open defects, DVIR, vehicle/telematics) are least-privilege. ground_vehicle and other writes pause with approval_required until a human approves. Investigator is read-only; Remediation is gated + sandboxed; Reviewer independently checks policy. One defect = one durable session with traces. How TrueFoundry is used / controls: - One governed MCP Gateway channel for ChatGPT, Claude, and Grok - Hosted stdio `fleet-demo-mock` â live Vercel fleet API - Approval gates on writes; session continuity and observability/traces - Least-privilege read vs write tools; sandbox + independent Reviewer - Second UI submission appears on the next agent ask with no MCP redeploy Demo script: 1. Open https://fleetheal.vercel.app and submit a crack-related DVIR. 2. In ChatGPT (MCP connected), ask for crack/open defects today and show TrueFoundry tool calls; optionally repeat in Claude/Grok. 3. Ask to ground TRK-4821 and show the approval_required pause. 4. Submit a second defect, ask again, and show it without redeploying MCP. Links: Live UI https://fleetheal.vercel.app | Repo https://github.com/OXmaint/fleetheal | MCP `fleet-demo-mock` with FLEETHEAL_API_BASE=https://fleetheal.vercel.app | Demo video: recording in portal
Built at The Agent Harness Hackathon
FleetHeal
Live end-to-end fleet remediation on TrueFoundry: Vercel DVIR UI â MCP Gateway (`fleet-demo-mock`) â ChatGPT + Claude + Grok as three harnesses on one governed channel â with approval-gated writes and full traces. Solution: FleetHeal is a production-shaped agent harness, not a chat toy. Inspectors submit defects, including crack-related flags, in a live Vercel UI. TrueFoundry MCP Gateway hosts `fleet-demo-mock` and live-reads the store via FLEETHEAL_API_BASE=https://fleetheal.vercel.app. ChatGPT, Claude, and Grok connect as separate harnesses to the SAME gateway; model choice is swappable while governance stays central. Read tools (open defects, DVIR, vehicle/telematics) are least-privilege. ground_vehicle and other writes pause with approval_required until a human approves. Investigator is read-only; Remediation is gated + sandboxed; Reviewer independently checks policy. One defect = one durable session with traces. How TrueFoundry is used / controls: - One governed MCP Gateway channel for ChatGPT, Claude, and Grok - Hosted stdio `fleet-demo-mock` â live Vercel fleet API - Approval gates on writes; session continuity and observability/traces - Least-privilege read vs write tools; sandbox + independent Reviewer - Second UI submission appears on the next agent ask with no MCP redeploy Demo script: 1. Open https://fleetheal.vercel.app and submit a crack-related DVIR. 2. In ChatGPT (MCP connected), ask for crack/open defects today and show TrueFoundry tool calls; optionally repeat in Claude/Grok. 3. Ask to ground TRK-4821 and show the approval_required pause. 4. Submit a second defect, ask again, and show it without redeploying MCP. Links: Live UI https://fleetheal.vercel.app | Repo https://github.com/OXmaint/fleetheal | MCP `fleet-demo-mock` with FLEETHEAL_API_BASE=https://fleetheal.vercel.app | Demo video: recording in portal
TrueFoundryMCP, App, Grok, GPT and Claude agents with TrueFoundry MCP gateway Keep exploring what builders shipped.
Sports Whisperer
SportsWhisperer
With AI becoming centre stage - Content and Entertainment will be the king. Sport has the highest amount of spend as industry and creates massive economic drive, so we have built an All in One - Sports Whisperer for all major sports Crickets, NFL, Soccer, Basketball, Baseball, etc where the novice and experienced players can interact with the favorite games and players !!! More details captured - https://docs.google.com/presentation/d/1_q0SDTvutQP9kd2SLdDXYYkc-h9QVYwj0vdih1Cuqzc/edit?slide=id.gcb9a0b074_1_0#slide=id.gcb9a0b074_1_0
AgentInvariant
AgentInvariant
AgentInvariant is a behavioral safety evaluator for tool-using AI agents. Agent workflows are probabilistic: two requests with the same meaning can produce materially different external actions. AgentInvariant uses metamorphic testing to determine whether critical operational behavior remains consistent across meaning-equivalent inputs. For each input variant, AgentInvariant starts a fresh OpenAI conversation and an isolated SQLite database. The target agent uses real tools to check coverage, retrieve authorization requirements, record business approval, and submit a synthetic prior-authorization request. AgentInvariant records the complete structured tool trace and evaluates it using deterministic Python invariants—not an LLM judge. It verifies that exactly one submission occurs and that matching coverage and business approval are successfully recorded before submission. The evaluator is exposed through a Streamable HTTP MCP server and invoked by a TrueForge agent using the `evaluate_agent` tool. Results include per-variant PASS or BLOCKED decisions, ordered traces, exact invariant violations, compliance rate, and the shortest failing counterexample. The demo compares an explicitly labeled unsafe negative control, which AgentInvariant correctly blocks, with a hardened candidate that follows the required workflow. All healthcare data is synthetic. This project is an administrative workflow reliability demonstration and is not clinical decision support.
HackerSquad project
Robo Harness
Hardess for robo