Conversation
- Rewrite README with problem statement, architecture diagram, comparison table, FAQ section, and polished quick start - Add CONTRIBUTING.md with dev setup and guidelines - Clean up CLAUDE.md for open-source contributors (remove local paths) - Remove internal docs (product design, context-module design doc) Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
README now leads with the problem, covers install/features/CLI/inspector concisely. Detailed API reference, embedding setup, sub-agent internals, migration, and manual setup moved to docs/ directory. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- OpenClaw: rewrite "What You Get" as user outcomes instead of implementation details, rename "Inspect Your Memory" to "Inspector" - Main: add missing import/backend setup to first Quick Start snippet Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Lead with the problem (CLAUDE.md is static, doesn't learn) - Outcome-focused "What You Get" - Remove 120-line competitive analysis with stale star counts - Add Inspector and Manage sections - Keep tools table, scopes, config, superseding example Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Streamline README: cleaner structure, consolidated results tables, remove verbose per-feature analysis - Remove unused suite, metric, and data scripts - Clean up exports and CLI references Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
lightcone0
added a commit
that referenced
this pull request
Mar 20, 2026
Backed by real developer complaints: GitHub Discussion #4845 (persistence is the #1 pain), AI SDK's own memory docs acknowledging the gap, and the existence of 4+ third-party memory providers. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
lightcone0
added a commit
that referenced
this pull request
Mar 20, 2026
Hooks into Pi's extension API for persistent cross-session memory. Fills the #1 community pain point — session amnesia. - 3 memory tools (write, search, list) registered via pi.registerTool() - Lifecycle hooks: fact extraction on turn_end, context injection on before_agent_start, reconciliation on session_shutdown - 7 tests covering tool registration, lifecycle events, fact extraction - README with researched pain points (Issue #1182, #92, #116, #1255), 5 use cases (project patterns, preferences, cross-project knowledge, surviving compaction, superseding), comparison with pi-hippocampus - Updated main README, publish.sh, architecture diagram Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Test plan
lishen,Li Shen,shenli)🤖 Generated with Claude Code