Open sourcePython · ≈770 stars · MIT
recall
Offline durable memory for Claude Code and OpenCode across sessions.
Recall gives Claude Code and OpenCode durable memory that works entirely offline, so project context does not have to be re-explained every session.
Activity
- Last push
- · 2mo ago
- Latest release
- v0.4.0
· 4mo ago - Last 90 days
- 0 releases
v0.4.0Recall 0.4.0 — OpenCode support (opt-in)
· 4mo agoRecall now works with opencode — the same fully-local memory (.recall/history.md + context.md), captured from opencode sessions instead of (or alongside) Claude Code. Requested in #10. Claude Code users: nothing changes. Claude Code remains the first-class harness. The hooks,…
v0.3.6Recall 0.3.6
· 4mo agoRecall now works on a standard Windows install. Previously the plugin would install and the slash commands would appear, but nothing was ever captured or surfaced — every failure was swallowed by the defensive handling that keeps Recall from crashing a Claude Code session.…
v0.3.5Recall 0.3.5
· 5mo agoNotes: Documentation release: adds a privacy policy. Added Privacy policy (PRIVACY.md), linked from the README. Documents that Recall runs fully locally — no network access, telemetry, accounts, or third-party/model calls, and all output stays under .recall/ — and that the…
v0.3.4Recall 0.3.4
· 5mo agoAdded Benchmark + quality harness (benchmarks/bench.py, stdlib-only): scores the summarizer's salient-sentence selection against lead/tail/random baselines and verifies both backends select identical sentences. --check gates these in CI on both the numpy and pure-Python paths.…
v0.3.3Recall 0.3.3
· 5mo agoFixed Malformed transcript lines no longer break capture. A single non-object JSONL line (or a turn whose message/tool input wasn't an object) raised an AttributeError; in the capture hook that error was swallowed and the byte offset never advanced, so history logging silently…
Checked against GitHub on Nov 21, 2026. Release notes are shortened to plain text.
Neighbours on the workbench
JavaScript · ≈308k stars · MIT
affaan-m/ECC
Agent harness performance optimization system: skills, instincts, memory and security for coding agents.
Maintained by Affaan Mustafa
TypeScript · ≈265k stars · MIT
NousResearch/hermes-agent
The agent that grows with you.
Maintained by Nous Research
v0.23.3releasedPython · ≈151k stars · Apache-2.0
Graphify-Labs/graphify
A /graphify skill that turns a codebase, docs and schemas into a queryable knowledge graph.
Maintained by Graphify-Labs
v0.9.114releasedConnections
Relations from the Harness Hub knowledge graph, as charted in the State of Harness reports.
Maintained by · 1
- raiyanyahyaOrganisation
Built on · 1
- Claude CodeProject
Similar entries · 3
- claude-smartProject
- CompartmentProject
- MemPalaceProject
Mentioned in · 11
- ChainAgent: Automated Chainable Vulnerability Discovery in PHP Web ApplicationsPaper · 2026-11-19
- FinVeriQA: Financial Research Agents for Question Answering: Routing, Retrieval, MCP Tool Use, and Provenance-Aware Evidence VerificationPaper · 2026-11-18
- YUL: Bringing Software Supply Chain Security to Coding AgentsPaper · 2026-11-13
- ReA-Bench: Benchmarking Responsible Agent AuditingPaper · 2026-11-12
- Adapting LLM-SC to Living Sacred Heritage: Domain-Specific Extraction, Semantic Networks and Human Evaluation on Pashupatinath Temple ReviewsPaper · 2026-10-26
- Reasoning Patterns for Efficient AI Coding: An Empirical StudyPaper · 2026-10-26
and 5 more
Sources
DisclosureAdded by Harness Hub's automated review of public metadata; not independently tested.
Verified Nov 18, 2026
