137,761 packages matching “context-injection”
@scitrera/memorylayer-opencode-plugin
v0.2.0 · 26 days ago
OpenCode plugin for MemoryLayer.ai - persistent memory hooks and context injection
No known vulnerabilities
@chenhw7/dsh-memory
v0.9.3 · 26 days ago
Cairn — long-term memory for the DeepSeek Harness: persistent cross-session memory (store, tools, auto-extraction, context injection) as one installable profile bundle
No known vulnerabilities
@minhpnq1807/contextos
v0.6.11 · 3 months ago
Task-aware AGENTS.md context injection and compliance reporting for Codex, Claude Code, and Antigravity.
No known vulnerabilities
@bleed00/dsh-claude-mem
v0.1.5 · 1 month ago
A DeepSeek Harness plugin that integrates claude-mem: query, context injection, manual save, and session lifecycle over a local claude-mem worker's HTTP API
No known vulnerabilities
@elementor-i/dsh-agentmemory
v0.1.4 · 1 month ago
agentmemory for DeepSeek Harness (dsh): full memory_* tools, capture hooks, and context injection over the local REST server
No known vulnerabilities
pi-openspec-context
v0.1.4 · 1 month ago
Lightweight Pi extension for automatic OpenSpec context injection into system prompts
No known vulnerabilities
@matthewfl/pi-simple-goal
v0.0.3 · 1 month ago
Keep Pi agents working toward a persistent goal with context injection, recovery prompts, and watchdog timers.
No known vulnerabilities
opencode-plugin-resumator
v0.6.1 · 1 month ago
OpenCode plugin for per-turn project context injection, technical state retention, and native compaction enrichment.
No known vulnerabilities
pi-qmd-ledger
v0.5.5 · 4 months ago
Universal configurable JSONL ledger with qmd hybrid search, tiered HITL, and dynamic context injection.
No known vulnerabilities
no-more-agents-dot-md
v1.3.1 · 26 days ago
No More Agents Dot MD: turn .pi/context/*.md files into declarative behavior rules (conditional context injection, tool guards, confirmations, input transforms, notifications) managed with the /nma command.
No known vulnerabilities
dsh-keyword-injector
v0.6.0 · 2 days ago
Context injection + behavioural guards for DSH: keyword triggers on user input or agent activity, tool-window guards, and agent-manageable trigger tools. POWERFUL AND DANGEROUS: lets AI agents shape each other's behaviour at any step — read the warnings b
No known vulnerabilities
@nexus-aethra/dshell-mode
v0.1.13 · 5 days ago
dshell mode toggle: per-session shell/agent mode state, composer Enter dispatch, /agent and /shell prefix parsing, and agent-mode terminal-context injection.
No known vulnerabilities
@zilliz/memsearch-dsh
v0.1.5 · 23 days ago
MemSearch plugin for DeepSeek Harness: shared markdown memory across agents, with capture, pre-step context injection, memory-recall skill, and a skill-candidate review panel.
No known vulnerabilities
claude-memory-fts
v2.0.1 · 5 months ago
Long-term memory MCP server for Claude Code with hybrid search (FTS5 + semantic), RRF ranking, and auto context injection
No known vulnerabilities
@snarkipus/opencode-beads
v0.10.0 · 27 days ago
A maintained OpenCode integration for the Beads issue tracker, including context injection, vendored workflows, and a task agent.
No known vulnerabilities
openspec-pi
v0.2.1 · 22 hours ago
OpenSpec deep integration for pi: native openspec tool, auto-context injection, /ospec command, plus official opsx prompts and openspec skills
No known vulnerabilities
@cadmus-ai/intelligence
v0.1.7 · 2 months ago
Cadmus Intelligence — code graph context injection for Cursor IDE
No known vulnerabilities
codex-evolution
v0.1.21 · 4 months ago
Project memory and SessionStart context injection for Codex.
No known vulnerabilities
dsh-surface-bridge
v0.1.0-alpha.8 · 3 days ago
Shared seam between a right-Sidebar business surface and the DSH composer: one selection chip, one Host-context injection point, one write-back channel
No known vulnerabilities
dsh-fast
v0.2.20 · 11 hours ago
Read-only performance diagnostics for DeepSeek Harness: session load (open/restore) timing, spill-hit counts, compaction count and trigger, context-injection volume (AGENTS.md/skills/tool-schema token share), and LLM cache hit rate — surfaced via the /fas
No known vulnerabilities