Self-hosted: Free, MIT licensed. Hindsight Cloud: Pay-as-you-go with free credits to start. Retain (store memories) $10.00 per million tokens, Recall (retrieve memories) $0.75 per million tokens, Reflect (synthesize patterns) $0.05 per call, Iris Extract (structured extraction) $7.50 per million tok
Key features
Governance: checks proposed AI actions against defined rules before execution
Recorded decision records that can be reviewed, replayed and verified later
Evaluation: compares AI agent performance using representative test cases and expected outcomes
Optimization: recommends model and cache candidates based on usage, prices and evaluation evidence
Regress detection identifies changed action paths and quality regressions
On-premises and private cloud deployment
Integration with existing AI tools via connectors and wrappers
No model training on customer data; separate data boundaries from external AI providers
Cost comparison and optimization across model and cache configurations
Per-user persistent memory with preferences, history and decisions kept separate
Cross-session persistence allows context to survive weeks between interactions
Fast parallel retrieval in under 100ms through four strategies running simultaneously
Works with any LLM without losing learned context when swapping models
Learns from mistakes and corrects behavior on repeated problems
Automatic pattern detection synthesizes individual facts into consolidated knowledge
Conflict detection preserves both old and new states with timestamps when facts change
Integrates with 20+ coding agents including Claude Code, Cursor, and Copilot
What makes it different
Independent accountability: checks run inside your systems, not asking another AI to audit AI
Your people keep authority: Forge produces decision evidence, your business enforces results
Recorded decision evidence that auditors and regulators can examine
Designed for consequential work in regulated industries like financial services
Not another dashboard: integrates into your workflow without replacing your AI tools
94.6% retrieval accuracy on LongMemEval-S, beating next-best system at 74.0%
MIT licensed open source with no usage limits, telemetry or restrictions
Reflection layer automatically builds judgment and mental models over time without manual tagging
Entity resolution handles hundreds of entities with 99.5% query reduction
Forge Orbital
Vectorize