KORE Universal Agent Services
https://triumphant-enthusiasm-production-02e1.up.railway.app/.well-known/agent.json
● healthy
16 services for AI agents: 13 universal infrastructure services (hallucination firewall ΨGuard, context compression ΔPack, semantic dedup ΩDeDup, cross-agent memory ΦMem, token cost arbitrage ΞRoute, prompt normalizer ΛNorm, quality scorer ΘScore, task decomposer ΣSplit, semantic diff ΓDiff, claim provenance ΠProve, embedding cache ΦEmbed, agent sandbox ΨSandbox, immutable audit log ΩAudit) plus 3 pay-per-use A2A-PIL task tools (research / reasoning / tool-use) billed per successful execution.
Transport
—
Protocol
1.1.0
Price
—
Skills
-
ΨGuard Hallucination FirewallLast gate before agent output emission. Flags unsupported claims.['safety', 'hallucination', 'guard', 'verification']
-
ΔPack Context Compression3-5x semantic compression without quality loss.['cost', 'compression', 'tokens', 'efficiency']
-
ΩDeDup Semantic DeduplicationCosine-similarity duplicate detection for RAG ingestion.['deduplication', 'rag', 'semantic', 'ingestion']
-
ΦMem Cross-Agent MemoryShared Qdrant-backed memory across all agents. Network effect.['memory', 'persistence', 'qdrant', 'swarm']
-
ΞRoute Token Cost ArbitrageRoutes to cheapest model that meets quality threshold.['routing', 'cost', 'optimization', 'fallback']
-
ΛNorm Prompt NormalizerStrips noise, detects injections, normalizes whitespace.['security', 'injection', 'normalization', 'sanitization']
-
ΘScore Output Quality ScorerRanks multiple candidate outputs by heuristic quality.['quality', 'scoring', 'ranking', 'evaluation']
-
ΣSplit Task DecomposerSplits complex tasks into parallel subtasks.['planning', 'decomposition', 'parallel', 'workflow']
-
ΓDiff Semantic Diff EngineMeaning-preserving diff between two text outputs.['diff', 'comparison', 'versioning', 'change-tracking']
-
ΠProve Claim ProvenanceEU AI Act compliant provenance certificates with hash chains.['compliance', 'provenance', 'eu-ai-act', 'hash-chain']
-
ΦEmbed Embedding CacheLRU-cached embeddings via all-MiniLM. Zero recomputation.['embedding', 'cache', 'vector', 'miniLM']
-
ΨSandbox Agent SandboxSafe code execution. No Docker needed. 30s timeout.['sandbox', 'execution', 'code', 'isolation']
-
ΩAudit Immutable Audit LogHMAC-SHA256 chained audit trail. EU AI Act compliant.['audit', 'compliance', 'hmac', 'tamper-evident']
-
A2A-PIL ResearchPay-per-use research task. 2 credits/successful execution. Cache hits, idempotent retries, failed executions, and rate-limited requests are NOT billed.['a2a', 'pil', 'pay-per-use', 'research']
-
A2A-PIL ReasoningPay-per-use reasoning task. 5 credits/successful execution. Cache hits, idempotent retries, failed executions, and rate-limited requests are NOT billed.['a2a', 'pil', 'pay-per-use', 'reasoning']
-
A2A-PIL Tool UsePay-per-use tool-use task. 10 credits/successful execution. Cache hits, idempotent retries, failed executions, and rate-limited requests are NOT billed.['a2a', 'pil', 'pay-per-use', 'tool-use']
How to call
A2A endpoint (JSONRPC)
https://triumphant-enthusiasm-production-02e1.up.railway.app
Listed in
Directories this entry was found in.
agenstry