Researchers at Mankind Research Labs in South Africa published Blast Radius on 7 August 2026, a predictive memory-management layer that cuts token consumption in agentic coding loops. Tested across seven OpenAI models, it reduced token use by 17–26%, achieved the lowest context-overflow rate among comparison policies, and maintained byte-exact reversibility—every eviction could be undone without information loss.

The core problem is structural. Each turn in an agentic loop re-submits the entire conversation: system prompt, tool schemas, prior file reads, diffs, stack traces. Cost grows with the sum of all prior context. A file dumped in full to fix a typo on turn 3 still occupies 2,000 tokens on turn 40, long after that sub-task closed. Authors MY Pitsane and Hope Mogale call this "pure epistemic entropy"—bandwidth consumed by noise rather than signal. The model pays attention-quadratic and dollar-linear costs to process context that can no longer affect the next action.

Existing strategies trade a recoverable cost (tokens) for an irrecoverable one (information). Sliding-window truncation drops the oldest tokens indiscriminately. Summarization compresses context through a second model call—itself fallible—and cannot be reversed if it discards something that matters later. Blast Radius estimates, before a turn executes, how far that turn will reach, then uses that estimate to license an eviction with bounded downside.

StrategyReversible?Information LossExtra CostMechanism
Sliding-window truncationNoHigh — oldest tokens dropped indiscriminatelyNoneDiscard oldest context at window boundary
SummarizationNoMedium — lossy compression via second modelExtra model call (itself fallible)Compress prior context through a second model call
Blast Radius / NECROPHORESISYesNone — context archived verbatimO(1)·κ per exhumation (fixed per-token cost)Predictive eviction; skeleton replaces archived block in-window
FIG. 02 Comparison of agentic-loop memory management strategies — Pitsane & Mogale, Blast Radius (Mankind Research Labs, 2026)

The architecture uses two channels. The context channel predicts the increment to the retained working set, converts that into an eviction budget, and applies a knapsack policy to select which dead context to archive. The code channel computes the churn-weighted set of files and symbols the turn's edits will touch through the dependency graph—the structural impact surface—and can checkpoint before changesets grow too large to review. Both answer: what is causally coupled to what I'm about to do?

Blast Radius two-channel architecture: context channel and code channel feeding into eviction and checkpoint decisions
FIG. 03 Blast Radius two-channel architecture: context channel and code channel feeding into eviction and checkpoint decisions — Pitsane & Mogale, Blast Radius (Mankind Research Labs, 2026)

Eviction is handled by NECROPHORESIS. Instead of discarding, it archives context verbatim and replaces it in-window with a skeleton. If wrong, restoration costs O(1)·κ—a single exhumation step at fixed per-token cost. Recurring Dead Matter (RDM) handles recurrence: it identifies near-identical transcripts injected repeatedly and buries entire classes using Laplace's rule. In test runs, 378 of 450 buried bodies (84%) were classified as recurring dead matter, and zero were recalled—every eviction held.

MetricResult
Token reduction vs. baseline17–26%
Context-overflow rateLowest among all comparison policies
Bodies buried (total)450
Classified as Recurring Dead Matter (RDM)378 (84%)
Evictions recalled (reversed)0
Restoration cost per exhumationO(1)·κ (fixed per-token)
FIG. 04 Blast Radius test results: eviction outcomes across 450 buried bodies — Pitsane & Mogale, Blast Radius (Mankind Research Labs, 2026)

Blast Radius operates beneath the HCRC gate, which controls admission. Division of labor is intentional: HCRC handles admission control, Blast Radius handles eviction selection. The information-theoretic framing connects context entropy to resurrection probability, arguing reversible forgetting reduces epistemic entropy without the finality that makes lossy approaches risky.

The work is a progress report toward Algosophy, a research program at Mankind Research Labs for making agentic coding reusable and sustainable. No open-source release is announced. The paper gives token-count reductions only, not dollar costs. Teams will need to map the 17–26% reduction to their own per-token pricing and call volume.

Takeaway: reversible eviction with a two-channel reach estimator is more defensible than truncation or summarization—but the 17–26% figure remains a benchmark to validate against your own loop depth and model mix until the code ships.